938 lines
36 KiB
HTML
938 lines
36 KiB
HTML
<h1 id="awesome-network-embedding">awesome-network-embedding</h1>
|
||
<p><a href="https://github.com/sindresorhus/awesome"><img
|
||
src="https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg"
|
||
alt="Awesome" /></a> <a href="http://makeapullrequest.com"><img
|
||
src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square"
|
||
alt="PRs Welcome" /></a> <a
|
||
href="https://gitter.im/awesome-network-embedding/Lobby"><img
|
||
src="https://badges.gitter.im/Join%20Chat.svg"
|
||
alt="Gitter chat for developers at https://gitter.im/dmlc/xgboost" /></a></p>
|
||
<p>Also called network representation learning, graph embedding,
|
||
knowledge embedding, etc.</p>
|
||
<p>The task is to learn the representations of the vertices from a given
|
||
network.</p>
|
||
<p>CALL FOR HELP: I’m planning to re-organize the papers with clear
|
||
classification index in the near future. Please feel free to submit a
|
||
commit if you find any interesting related work:)</p>
|
||
<p><img src="NE.png" width="480"></p>
|
||
<h1 id="paper-references-with-the-implementations">Paper References with
|
||
the implementation(s)</h1>
|
||
<ul>
|
||
<li><strong>GraphGym</strong>
|
||
<ul>
|
||
<li>A platform for designing and evaluating Graph Neural Networks (GNN),
|
||
NeurIPS 2020</li>
|
||
<li><a
|
||
href="https://proceedings.neurips.cc/paper/2020/file/c5c3d4fe6b2cc463c7d7ecba17cc9de7-Paper.pdf">[Paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/snap-stanford/graphgym">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>FEATHER</strong>
|
||
<ul>
|
||
<li>Characteristic Functions on Graphs: Birds of a Feather, from
|
||
Statistical Descriptors to Parametric Models, CIKM 2020</li>
|
||
<li><a href="https://arxiv.org/abs/2005.07959">[Paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/FEATHER">[Python]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>HeGAN</strong>
|
||
<ul>
|
||
<li>Adversarial Learning on Heterogeneous Information Networks, KDD
|
||
2019</li>
|
||
<li><a
|
||
href="https://fangyuan1st.github.io/paper/KDD19_HeGAN.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/librahu/HeGAN">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>NetMF</strong>
|
||
<ul>
|
||
<li>Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE,
|
||
PTE, and Node2Vec, WSDM 2018</li>
|
||
<li><a
|
||
href="https://keg.cs.tsinghua.edu.cn/jietang/publications/WSDM18-Qiu-et-al-NetMF-network-embedding.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>GL2Vec</strong>
|
||
<ul>
|
||
<li>GL2vec: Graph Embedding Enriched by Line Graphs with Edge Features,
|
||
ICONIP 2019</li>
|
||
<li><a
|
||
href="https://link.springer.com/chapter/10.1007/978-3-030-36718-3_1">[Paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>NNSED</strong>
|
||
<ul>
|
||
<li>A Non-negative Symmetric Encoder-Decoder Approach for Community
|
||
Detection, CIKM 2017</li>
|
||
<li><a
|
||
href="http://www.bigdatalab.ac.cn/~shenhuawei/publications/2017/cikm-sun.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>SymmNMF</strong>
|
||
<ul>
|
||
<li>Symmetric Nonnegative Matrix Factorization for Graph Clustering, SDM
|
||
2012</li>
|
||
<li><a
|
||
href="https://www.cc.gatech.edu/~hpark/papers/DaDingParkSDM12.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>RECT</strong>
|
||
<ul>
|
||
<li>Network Embedding with Completely-Imbalanced Labels, TKDE 2020</li>
|
||
<li><a
|
||
href="https://zhengwang100.github.io/pdf/TKDE20_wzheng.pdf">[Paper]</a></li>
|
||
<li><a href="https://github.com/zhengwang100/RECT">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>GEMSEC</strong>
|
||
<ul>
|
||
<li>GEMSEC: Graph Embedding with Self Clustering, ASONAM 2019</li>
|
||
<li><a href="https://arxiv.org/abs/1802.03997">[Paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/GEMSEC">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>AmpliGraph</strong>
|
||
<ul>
|
||
<li>Library for learning knowledge graph embeddings with TensorFlow</li>
|
||
<li><a href="http://docs.ampligraph.org">[Project]</a></li>
|
||
<li><a href="https://github.com/Accenture/AmpliGraph">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>jodie</strong>
|
||
<ul>
|
||
<li>Predicting Dynamic Embedding Trajectory in Temporal Interaction
|
||
Networks, KDD’19</li>
|
||
<li><a href="http://snap.stanford.edu/jodie/">[Project]</a></li>
|
||
<li><a href="https://github.com/srijankr/jodie/">[Code]</a></li>
|
||
</ul></li>
|
||
<li><strong>PyTorch-BigGraph</strong>
|
||
<ul>
|
||
<li>Pytorch-BigGraph - a distributed system for learning graph
|
||
embeddings for large graphs, SysML’19</li>
|
||
<li><a
|
||
href="https://github.com/facebookresearch/PyTorch-BigGraph">[github]</a></li>
|
||
</ul></li>
|
||
<li><strong>ATP</strong>
|
||
<ul>
|
||
<li>ATP: Directed Graph Embedding with Asymmetric Transitivity
|
||
Preservation, AAAI’19</li>
|
||
<li><a href="https://arxiv.org/abs/1811.00839">[paper]</a></li>
|
||
<li><a href="https://github.com/zhenv5/atp">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>MUSAE</strong>
|
||
<ul>
|
||
<li>Multi-scale Attributed Node Embedding, ArXiv 2019</li>
|
||
<li><a href="https://arxiv.org/abs/1909.13021">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/MUSAE">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>SEAL-CI</strong>
|
||
<ul>
|
||
<li>Semi-Supervised Graph Classification: A Hierarchical Graph
|
||
Perspective, WWW’19</li>
|
||
<li><a href="https://arxiv.org/pdf/1904.05003.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/SEAL-CI">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>N-GCN and MixHop</strong>
|
||
<ul>
|
||
<li>A Higher-Order Graph Convolutional Layer, NIPS’18 (workshop)</li>
|
||
<li><a
|
||
href="http://sami.haija.org/papers/high-order-gc-layer.pdf">[paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/MixHop-and-N-GCN">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>CapsGNN</strong>
|
||
<ul>
|
||
<li>Capsule Graph Neural Network, ICLR’19</li>
|
||
<li><a
|
||
href="https://openreview.net/forum?id=Byl8BnRcYm">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/CapsGNN">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>Splitter</strong>
|
||
<ul>
|
||
<li>Splitter: Learning Node Representations that Capture Multiple Social
|
||
Contexts, WWW’19</li>
|
||
<li><a
|
||
href="http://epasto.org/papers/www2019splitter.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/Splitter">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>REGAL</strong>
|
||
<ul>
|
||
<li>REGAL: Representation Learning-based Graph Alignment. International
|
||
Conference on Information and Knowledge Management, CIKM’18</li>
|
||
<li><a href="https://arxiv.org/pdf/1802.06257.pdf">[arxiv]</a></li>
|
||
<li><a
|
||
href="https://dl.acm.org/citation.cfm?id=3271788">[paper]</a></li>
|
||
<li><a href="https://github.com/GemsLab/REGAL">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>PyTorch Geometric</strong>
|
||
<ul>
|
||
<li>Fast Graph Representation Learning With PyTorch Geometric</li>
|
||
<li><a href="https://arxiv.org/pdf/1903.02428.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/rusty1s/pytorch_geometric">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>TuckER</strong>
|
||
<ul>
|
||
<li>Tensor Factorization for Knowledge Graph Completion, Arxiv’19</li>
|
||
<li><a href="https://arxiv.org/pdf/1901.09590.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/ibalazevic/TuckER">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>HypER</strong>
|
||
<ul>
|
||
<li>Hypernetwork Knowledge Graph Embeddings, Arxiv’18</li>
|
||
<li><a href="https://arxiv.org/pdf/1808.07018.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/ibalazevic/HypER">[Python
|
||
PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>GWNN</strong>
|
||
<ul>
|
||
<li>Graph Wavelet Neural Network, ICLR’19</li>
|
||
<li><a
|
||
href="https://openreview.net/forum?id=H1ewdiR5tQ">[paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork">[Python
|
||
PyTorch]</a></li>
|
||
<li><a href="https://github.com/Eilene/GWNN">[Python
|
||
TensorFlow]</a></li>
|
||
</ul></li>
|
||
<li><strong>APPNP</strong>
|
||
<ul>
|
||
<li>Combining Neural Networks with Personalized PageRank for
|
||
Classification on Graphs, ICLR’19</li>
|
||
<li><a href="https://arxiv.org/abs/1810.05997">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/APPNP">[Python
|
||
PyTorch]</a></li>
|
||
<li><a href="https://github.com/klicperajo/ppnp">[Python
|
||
TensorFlow]</a></li>
|
||
</ul></li>
|
||
<li><strong>role2vec</strong>
|
||
<ul>
|
||
<li>Learning Role-based Graph Embeddings, IJCAI’18</li>
|
||
<li><a href="https://arxiv.org/pdf/1802.02896.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/role2vec">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>AttentionWalk</strong>
|
||
<ul>
|
||
<li>Watch Your Step: Learning Node Embeddings via Graph Attention,
|
||
NIPS’18</li>
|
||
<li><a href="https://arxiv.org/pdf/1710.09599.pdf">[paper]</a></li>
|
||
<li><a href="http://sami.haija.org/graph/context">[Python]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/AttentionWalk">[Python
|
||
PyTorch]</a></li>
|
||
<li><a
|
||
href="https://github.com/google-research/google-research/tree/master/graph_embedding/watch_your_step/">[Python
|
||
TensorFlow]</a></li>
|
||
</ul></li>
|
||
<li><strong>GAT</strong>
|
||
<ul>
|
||
<li>Graph Attention Networks, ICLR’18</li>
|
||
<li><a href="https://arxiv.org/pdf/1710.10903.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/Diego999/pyGAT">[Python
|
||
PyTorch]</a></li>
|
||
<li><a href="https://github.com/PetarV-/GAT">[Python
|
||
TensorFlow]</a></li>
|
||
</ul></li>
|
||
<li><strong>SINE</strong>
|
||
<ul>
|
||
<li>SINE: Scalable Incomplete Network Embedding, ICDM’18</li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/SINE/blob/master/paper.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/SINE/">[Python
|
||
PyTorch]</a></li>
|
||
<li><a href="https://github.com/daokunzhang/SINE">[C++]</a></li>
|
||
</ul></li>
|
||
<li><strong>SGCN</strong>
|
||
<ul>
|
||
<li>Signed Graph Convolutional Network, ICDM’18</li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/SGCN/blob/master/sgcn.pdf">[paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/SGCN">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>TENE</strong>
|
||
<ul>
|
||
<li>Enhanced Network Embedding with Text Information, ICPR’18</li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/TENE/blob/master/tene_paper.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/TENE">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>DANMF</strong>
|
||
<ul>
|
||
<li>Deep Autoencoder-like Nonnegative Matrix Factorization for Community
|
||
Detection, CIKM’18</li>
|
||
<li><a
|
||
href="https://smartyfh.com/Documents/18DANMF.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/DANMF">[Python]</a></li>
|
||
<li><a href="https://github.com/smartyfh/DANMF">[Matlab]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>BANE</strong>
|
||
<ul>
|
||
<li>Binarized Attributed Network Embedding, ICDM’18</li>
|
||
<li><a
|
||
href="https://www.researchgate.net/publication/328688614_Binarized_Attributed_Network_Embedding">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/BANE">[Python]</a></li>
|
||
<li><a href="https://github.com/ICDM2018-BANE/BANE">[Matlab]</a></li>
|
||
</ul></li>
|
||
<li><strong>GCN Insights</strong>
|
||
<ul>
|
||
<li>Deeper Insights into Graph Convolutional Networks for
|
||
Semi-Supervised Learning, AAAI’18</li>
|
||
<li><a href="https://liqimai.github.io/blog/AAAI-18/">[Project]</a></li>
|
||
<li><a
|
||
href="https://github.com/liqimai/gcn/tree/AAAI-18/">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>PCTADW</strong>
|
||
<ul>
|
||
<li>Learning Embeddings of Directed Networks with Text-Associated
|
||
Nodes—with Applications in Software Package Dependency Networks</li>
|
||
<li><a href="https://arxiv.org/pdf/1809.02270.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/shudan/PCTADW">[Python]</a></li>
|
||
<li><a href="https://doi.org/10.5281/zenodo.1410669">[dataset]</a></li>
|
||
</ul></li>
|
||
<li><strong>LGCN</strong>
|
||
<ul>
|
||
<li>Large-Scale Learnable Graph Convolutional Networks, KDD’18</li>
|
||
<li><a
|
||
href="http://www.kdd.org/kdd2018/accepted-papers/view/large-scale-learnable-graph-convolutional-networks">[paper]</a></li>
|
||
<li><a href="https://github.com/HongyangGao/LGCN">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>AspEm</strong>
|
||
<ul>
|
||
<li>AspEm: Embedding Learning by Aspects in Heterogeneous Information
|
||
Networks</li>
|
||
<li><a
|
||
href="http://yushi2.web.engr.illinois.edu/sdm18.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/ysyushi/aspem">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>Walklets</strong>
|
||
<ul>
|
||
<li>Don’t Walk, Skip! Online Learning of Multi-scale Network
|
||
Embeddings</li>
|
||
<li><a href="https://arxiv.org/pdf/1605.02115.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
Karateclub]</a><br />
|
||
</li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/walklets">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>gat2vec</strong>
|
||
<ul>
|
||
<li>gat2vec: Representation learning for attributed graphs</li>
|
||
<li><a href="https://doi.org/10.1007/s00607-018-0622-9">[paper]</a></li>
|
||
<li><a href="https://github.com/snash4/GAT2VEC">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>FSCNMF</strong>
|
||
<ul>
|
||
<li>FSCNMF: Fusing Structure and Content via Non-negative Matrix
|
||
Factorization for Embedding Information Networks</li>
|
||
<li><a href="https://arxiv.org/abs/1804.05313">[paper]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
Karateclub]</a></li>
|
||
<li><a href="https://github.com/sambaranban/FSCNMF">[Python]</a><br />
|
||
</li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/FSCNMF">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>SIDE</strong>
|
||
<ul>
|
||
<li>SIDE: Representation Learning in Signed Directed Networks</li>
|
||
<li><a
|
||
href="https://datalab.snu.ac.kr/side/resources/side.pdf">[paper]</a></li>
|
||
<li><a
|
||
href="https://datalab.snu.ac.kr/side/resources/side.zip">[Python]</a></li>
|
||
<li><a href="https://datalab.snu.ac.kr/side/">[Site]</a></li>
|
||
</ul></li>
|
||
<li><strong>AWE</strong>
|
||
<ul>
|
||
<li>Anonymous Walk Embeddings, ICML’18</li>
|
||
<li><a
|
||
href="https://www.researchgate.net/publication/325114285_Anonymous_Walk_Embeddings">[paper]</a></li>
|
||
<li><a
|
||
href="https://github.com/nd7141/Anonymous-Walk-Embeddings">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>BiNE</strong>
|
||
<ul>
|
||
<li>BiNE: Bipartite Network Embedding, SIGIR’18</li>
|
||
<li><a
|
||
href="http://staff.ustc.edu.cn/~hexn/papers/sigir18-bipartiteNE.pdf">[paper]</a></li>
|
||
<li><a href="https://github.com/clhchtcjj/BiNE">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>HOPE</strong>
|
||
<ul>
|
||
<li>Asymmetric Transitivity Preserving Graph Embedding</li>
|
||
<li><a
|
||
href="http://www.kdd.org/kdd2016/papers/files/rfp0184-ouA.pdf">[KDD
|
||
2016]</a></li>
|
||
<li><a href="https://github.com/AnryYang/HOPE">[Python]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>VERSE</strong>
|
||
<ul>
|
||
<li>VERSE, Versatile Graph Embeddings from Similarity Measures</li>
|
||
<li><a href="https://arxiv.org/abs/1803.04742">[Arxiv]</a> [[WWW
|
||
2018]]</li>
|
||
<li><a href="https://github.com/xgfs/verse">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>AGNN</strong>
|
||
<ul>
|
||
<li>Attention-based Graph Neural Network for semi-supervised
|
||
learning</li>
|
||
<li><a href="https://openreview.net/forum?id=rJg4YGWRb">[ICLR 2018
|
||
OpenReview (rejected)]</a></li>
|
||
<li><a
|
||
href="https://github.com/dawnranger/pytorch-AGNN">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>SEANO</strong>
|
||
<ul>
|
||
<li>Semi-supervised Embedding in Attributed Networks with Outliers</li>
|
||
<li><a href="https://arxiv.org/pdf/1703.08100.pdf">[Paper]</a> (SDM
|
||
2018)</li>
|
||
<li><a href="http://jiongqianliang.com/SEANO/">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>Hyperbolics</strong>
|
||
<ul>
|
||
<li>Representation Tradeoffs for Hyperbolic Embeddings</li>
|
||
<li><a href="https://arxiv.org/abs/1804.03329">[Arxiv]</a></li>
|
||
<li><a
|
||
href="https://github.com/HazyResearch/hyperbolics">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>DGCNN</strong>
|
||
<ul>
|
||
<li>An End-to-End Deep Learning Architecture for Graph
|
||
Classification</li>
|
||
<li><a
|
||
href="http://www.cse.wustl.edu/~muhan/papers/AAAI_2018_DGCNN.pdf">[AAAI
|
||
2018]</a></li>
|
||
<li><a href="https://github.com/muhanzhang/DGCNN">[Lua]</a> <a
|
||
href="https://github.com/muhanzhang/pytorch_DGCNN">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>structure2vec</strong>
|
||
<ul>
|
||
<li>Discriminative Embeddings of Latent Variable Models for Structured
|
||
Data</li>
|
||
<li><a href="https://arxiv.org/abs/1603.05629">[Arxiv]</a></li>
|
||
<li><a
|
||
href="https://github.com/Hanjun-Dai/pytorch_structure2vec">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>Decagon</strong>
|
||
<ul>
|
||
<li>Decagon, Graph Neural Network for Multirelational Link
|
||
Prediction</li>
|
||
<li><a href="https://arxiv.org/abs/1802.00543">[Arxiv]</a> <a
|
||
href="http://snap.stanford.edu/decagon/">[SNAP]</a> [[ISMB 2018]]</li>
|
||
<li><a href="https://github.com/marinkaz/decagon">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>DHNE</strong>
|
||
<ul>
|
||
<li>Structural Deep Embedding for Hyper-Networks</li>
|
||
<li><a
|
||
href="http://nrl.thumedialab.com/Structural-Deep-Embedding-for-Hyper-Networks">[AAAI
|
||
2018]</a><a href="https://arxiv.org/abs/1711.10146">[Arxiv]</a></li>
|
||
<li><a href="https://github.com/tadpole/DHNE">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>Ohmnet</strong>
|
||
<ul>
|
||
<li>Feature Learning in Multi-Layer Networks</li>
|
||
<li><a href="https://arxiv.org/abs/1707.04638">[Arxiv]</a> <a
|
||
href="http://snap.stanford.edu/ohmnet/">[SNAP]</a></li>
|
||
<li><a href="https://github.com/marinkaz/ohmnet">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>SDNE</strong>
|
||
<ul>
|
||
<li>Structural Deep Network Embedding</li>
|
||
<li><a
|
||
href="http://www.kdd.org/kdd2016/papers/files/rfp0191-wangAemb.pdf">[KDD
|
||
2016]</a></li>
|
||
<li><a
|
||
href="https://github.com/xiaohan2012/sdne-keras">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>STWalk</strong>
|
||
<ul>
|
||
<li>STWalk: Learning Trajectory Representations in Temporal Graphs]</li>
|
||
<li><a href="https://arxiv.org/abs/1711.04150">[Arxiv]</a></li>
|
||
<li><a
|
||
href="https://github.com/supriya-pandhre/STWalk">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>LoNGAE</strong>
|
||
<ul>
|
||
<li>Learning to Make Predictions on Graphs with Autoencoders</li>
|
||
<li><a href="https://arxiv.org/abs/1802.08352">[Arxiv]</a></li>
|
||
<li><a
|
||
href="https://github.com/vuptran/graph-representation-learning">[Python]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>RSDNE</strong>
|
||
<ul>
|
||
<li><a href="https://zhengwang100.github.io/AAAI18_RSDNE.pdf">RSDNE:
|
||
Exploring Relaxed Similarity and Dissimilarity from
|
||
Completely-imbalanced Labels for Network Embedding.</a>, AAAI 2018</li>
|
||
<li><a href="https://github.com/zhengwang100/RSDNE">[Matlab]</a></li>
|
||
</ul></li>
|
||
<li><strong>FastGCN</strong>
|
||
<ul>
|
||
<li>FastGCN: Fast Learning with Graph Convolutional Networks via
|
||
Importance Sampling</li>
|
||
<li><a href="https://arxiv.org/abs/1801.10247">[Arxiv]</a>, <a
|
||
href="https://openreview.net/forum?id=rytstxWAW">[ICLR 2018
|
||
OpenReview]</a></li>
|
||
<li><a href="https://github.com/matenure/FastGCN">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>diff2vec</strong>
|
||
<ul>
|
||
<li><a
|
||
href="http://homepages.inf.ed.ac.uk/s1668259/papers/sequence.pdf">Fast
|
||
Sequence Based Embedding with Diffusion Graphs</a>, CompleNet 2018</li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/diff2vec">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>Poincare</strong>
|
||
<ul>
|
||
<li><a
|
||
href="https://papers.nips.cc/paper/7213-poincare-embeddings-for-learning-hierarchical-representations">Poincaré
|
||
Embeddings for Learning Hierarchical Representations</a>, NIPS 2017</li>
|
||
<li><a
|
||
href="https://github.com/facebookresearch/poincare-embeddings">[PyTorch]</a>
|
||
<a
|
||
href="https://radimrehurek.com/gensim/models/poincare.html">[Python]</a>
|
||
<a
|
||
href="https://github.com/TatsuyaShirakawa/poincare-embedding">[C++]</a></li>
|
||
</ul></li>
|
||
<li><strong>PEUNE</strong>
|
||
<ul>
|
||
<li><a
|
||
href="https://papers.nips.cc/paper/7110-prune-preserving-proximity-and-global-ranking-for-network-embedding">PRUNE:
|
||
Preserving Proximity and Global Ranking for Network Embedding</a>, NIPS
|
||
2017</li>
|
||
<li><a href="https://github.com/ntumslab/PRUNE">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>ASNE</strong>
|
||
<ul>
|
||
<li>Attributed Social Network Embedding, TKDE’18</li>
|
||
<li><a href="https://arxiv.org/abs/1706.01860">[arxiv]</a></li>
|
||
<li><a href="https://github.com/lizi-git/ASNE">[Python]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/ASNE">[Fast
|
||
Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>GraphWave</strong>
|
||
<ul>
|
||
<li><a href="http://snap.stanford.edu/graphwave/">Spectral Graph
|
||
Wavelets for Structural Role Similarity in Networks</a>,</li>
|
||
<li><a href="https://arxiv.org/abs/1710.10321">[arxiv]</a>, <a
|
||
href="https://openreview.net/forum?id=rytstxWAW">[ICLR 2018
|
||
OpenReview]</a></li>
|
||
<li><a href="https://github.com/snap-stanford/graphwave">[Python]</a> <a
|
||
href="https://github.com/benedekrozemberczki/GraphWaveMachine">[faster
|
||
version]</a></li>
|
||
</ul></li>
|
||
<li><strong>StarSpace</strong>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1709.03856">StarSpace: Embed All The
|
||
Things!</a>, arxiv’17</li>
|
||
<li><a
|
||
href="https://github.com/facebookresearch/Starspace">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>proNet-core</strong>
|
||
<ul>
|
||
<li>Vertex-Context Sampling for Weighted Network Embedding,
|
||
arxiv’17</li>
|
||
<li><a href="https://arxiv.org/abs/1711.00227">[arxiv]</a> <a
|
||
href="https://github.com/cnclabs/proNet-core">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>struc2vec</strong>
|
||
<ul>
|
||
<li><a href="https://dl.acm.org/citation.cfm?id=3098061">struc2vec:
|
||
Learning Node Representations from Structural Identity</a>, KDD’17</li>
|
||
<li><a href="https://github.com/leoribeiro/struc2vec">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>ComE</strong>
|
||
<ul>
|
||
<li>Learning Community Embedding with Community Detection and Node
|
||
Embedding on Graphs, CIKM’17</li>
|
||
<li><a href="https://github.com/andompesta/ComE">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>BoostedNE</strong>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/abs/1808.08627">Multi-Level Network
|
||
Embedding with Boosted Low-Rank Matrix Approximation</a>, ’18</li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/BoostedFactorization">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>M-NMF</strong>
|
||
<ul>
|
||
<li>Community Preserving Network Embedding, AAAI’17</li>
|
||
<li><a href="https://github.com/benedekrozemberczki/M-NMF">[Python
|
||
TensorFlow]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>GraphSAGE</strong>
|
||
<ul>
|
||
<li>Inductive Representation Learning on Large Graphs, NIPS’17</li>
|
||
<li><a href="https://arxiv.org/abs/1706.02216">[arxiv]</a> <a
|
||
href="https://github.com/williamleif/GraphSAGE">[TF]</a> <a
|
||
href="https://github.com/williamleif/graphsage-simple/">[PyTorch]</a></li>
|
||
</ul></li>
|
||
<li><strong>ICE</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=3080807">ICE: Item
|
||
Concept Embedding via Textual Information</a>, SIGIR’17</li>
|
||
<li><a href="https://cnclabs.github.io/ICE/">[demo]</a> <a
|
||
href="https://github.com/cnclabs/ICE">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>GuidedHeteEmbedding</strong>
|
||
<ul>
|
||
<li>Task-guided and path-augmented heterogeneous network embedding for
|
||
author identification, WSDM’17</li>
|
||
<li><a href="https://arxiv.org/pdf/1612.02814.pdf">[paper]</a> <a
|
||
href="https://github.com/chentingpc/GuidedHeteEmbedding">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>metapath2vec</strong>
|
||
<ul>
|
||
<li>metapath2vec: Scalable Representation Learning for Heterogeneous
|
||
Networks, KDD’17</li>
|
||
<li><a
|
||
href="https://www3.nd.edu/~dial/publications/dong2017metapath2vec.pdf">[paper]</a>
|
||
<a href="https://ericdongyx.github.io/metapath2vec/m2v.html">[project
|
||
website]</a></li>
|
||
</ul></li>
|
||
<li><strong>GCN</strong>
|
||
<ul>
|
||
<li>Semi-Supervised Classification with Graph Convolutional Networks,
|
||
ICLR’17</li>
|
||
<li><a href="https://arxiv.org/abs/1609.02907">[arxiv]</a> <a
|
||
href="https://github.com/tkipf/gcn">[Python Tensorflow]</a></li>
|
||
</ul></li>
|
||
<li><strong>GAE</strong>
|
||
<ul>
|
||
<li>Variational Graph Auto-Encoders, arxiv</li>
|
||
<li><a href="https://arxiv.org/abs/1611.07308">[arxiv]</a> <a
|
||
href="https://github.com/tkipf/gae">[Python Tensorflow]</a></li>
|
||
</ul></li>
|
||
<li><strong>CANE</strong>
|
||
<ul>
|
||
<li>CANE: Context-Aware Network Embedding for Relation Modeling,
|
||
ACL’17</li>
|
||
<li><a
|
||
href="http://www.thunlp.org/~tcc/publications/acl2017_cane.pdf">[paper]</a>
|
||
<a href="https://github.com/thunlp/cane">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>TransNet</strong>
|
||
<ul>
|
||
<li>TransNet: Translation-Based Network Representation Learning for
|
||
Social Relation Extraction, IJCAI’17</li>
|
||
<li><a href="https://github.com/thunlp/TransNet">[Python
|
||
Tensorflow]</a></li>
|
||
</ul></li>
|
||
<li><strong>cnn_graph</strong>
|
||
<ul>
|
||
<li>Convolutional Neural Networks on Graphs with Fast Localized Spectral
|
||
Filtering, NIPS’16</li>
|
||
<li><a href="https://github.com/mdeff/cnn_graph">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>ConvE</strong>
|
||
<ul>
|
||
<li><a href="https://arxiv.org/pdf/1707.01476v2.pdf">Convolutional 2D
|
||
Knowledge Graph Embeddings</a>, arxiv</li>
|
||
<li><a href="https://github.com/TimDettmers/ConvE">[source]</a></li>
|
||
</ul></li>
|
||
<li><strong>node2vec</strong>
|
||
<ul>
|
||
<li><a
|
||
href="http://dl.acm.org/citation.cfm?id=2939672.2939754">node2vec:
|
||
Scalable Feature Learning for Networks</a>, KDD’16</li>
|
||
<li><a href="https://arxiv.org/abs/1607.00653">[arxiv]</a> <a
|
||
href="https://github.com/aditya-grover/node2vec">[Python]</a> <a
|
||
href="https://github.com/apple2373/node2vec">[Python-2]</a> <a
|
||
href="https://github.com/eliorc/node2vec">[Python-3]</a> <a
|
||
href="https://github.com/xgfs/node2vec-c">[C++]</a><br />
|
||
</li>
|
||
</ul></li>
|
||
<li><strong>DNGR</strong>
|
||
<ul>
|
||
<li><a
|
||
href="http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12423">Deep
|
||
Neural Networks for Learning Graph Representations</a>, AAAI’16</li>
|
||
<li><a href="https://github.com/ShelsonCao/DNGR">[Matlab]</a> <a
|
||
href="https://github.com/MdAsifKhan/DNGR-Keras">[Python Keras]</a></li>
|
||
</ul></li>
|
||
<li><strong>HolE</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=3016172">Holographic
|
||
Embeddings of Knowledge Graphs</a>, AAAI’16</li>
|
||
<li><a
|
||
href="https://github.com/mnick/holographic-embeddings">[Python-sklearn]</a>
|
||
<a href="https://github.com/mnick/scikit-kge">[Python-sklearn2]</a></li>
|
||
</ul></li>
|
||
<li><strong>ComplEx</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=3045609">Complex
|
||
Embeddings for Simple Link Prediction</a>, ICML’16</li>
|
||
<li><a href="https://arxiv.org/abs/1606.06357">[arxiv]</a> <a
|
||
href="https://github.com/ttrouill/complex">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>MMDW</strong>
|
||
<ul>
|
||
<li>Max-Margin DeepWalk: Discriminative Learning of Network
|
||
Representation, IJCAI’16</li>
|
||
<li><a
|
||
href="http://nlp.csai.tsinghua.edu.cn/~lzy/publications/ijcai2016_mmdw.pdf">[paper]</a>
|
||
<a href="https://github.com/thunlp/MMDW">[Java]</a></li>
|
||
</ul></li>
|
||
<li><strong>planetoid</strong>
|
||
<ul>
|
||
<li>Revisiting Semi-supervised Learning with Graph Embeddings,
|
||
ICML’16</li>
|
||
<li><a href="https://arxiv.org/abs/1603.08861">[arxiv]</a> <a
|
||
href="https://github.com/kimiyoung/planetoid">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>graph2vec</strong>
|
||
<ul>
|
||
<li>graph2vec: Learning Distributed Representations of Graphs, KDD’17
|
||
MLGWorkshop</li>
|
||
<li><a href="https://arxiv.org/abs/1707.05005">[arxiv]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/graph2vec">[Python
|
||
gensim]</a> <a
|
||
href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>PowerWalk</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2983713">PowerWalk:
|
||
Scalable Personalized PageRank via Random Walks with Vertex-Centric
|
||
Decomposition</a>, CIKM’16</li>
|
||
<li><a href="https://github.com/lqhl/PowerWalk">[code]</a></li>
|
||
</ul></li>
|
||
<li><strong>LINE</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2741093">LINE:
|
||
Large-scale information network embedding</a>, WWW’15</li>
|
||
<li><a href="https://arxiv.org/abs/1503.03578">[arxiv]</a> <a
|
||
href="https://github.com/tangjianpku/LINE">[C++]</a> <a
|
||
href="https://github.com/snowkylin/line">[Python TF]</a> <a
|
||
href="https://github.com/VahidooX/LINE">[Python Theano/Keras]</a></li>
|
||
</ul></li>
|
||
<li><strong>PTE</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2783307">PTE: Predictive
|
||
Text Embedding through Large-scale Heterogeneous Text Networks</a>,
|
||
KDD’15</li>
|
||
<li><a href="https://github.com/mnqu/PTE">[C++]</a></li>
|
||
</ul></li>
|
||
<li><strong>GraRep</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2806512">Grarep: Learning
|
||
graph representations with global structural information</a>,
|
||
CIKM’15</li>
|
||
<li><a href="https://github.com/ShelsonCao/GraRep">[Matlab]</a></li>
|
||
<li><a href="https://github.com/xgfs/GraRep.jl">[Julia]</a></li>
|
||
<li><a
|
||
href="https://github.com/benedekrozemberczki/GraRep">[Python]</a></li>
|
||
<li><a href="https://github.com/benedekrozemberczki/karateclub">[Python
|
||
KarateClub]</a></li>
|
||
</ul></li>
|
||
<li><strong>KB2E</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2886624">Learning Entity
|
||
and Relation Embeddings for Knowledge Graph Completion</a>, AAAI’15</li>
|
||
<li><a
|
||
href="http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf">[paper]</a>
|
||
<a href="https://github.com/thunlp/KB2E">[C++]</a> <a
|
||
href="https://github.com/thunlp/Fast-TransX">[faster version]</a></li>
|
||
</ul></li>
|
||
<li><strong>TADW</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2832542">Network
|
||
Representation Learning with Rich Text Information</a>, IJCAI’15</li>
|
||
<li><a
|
||
href="https://www.ijcai.org/Proceedings/15/Papers/299.pdf">[paper]</a>
|
||
<a href="https://github.com/thunlp/tadw">[Matlab]</a> <a
|
||
href="https://github.com/benedekrozemberczki/TADW">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>DeepWalk</strong>
|
||
<ul>
|
||
<li><a href="http://dl.acm.org/citation.cfm?id=2623732">DeepWalk: Online
|
||
Learning of Social Representations</a>, KDD’14</li>
|
||
<li><a href="https://arxiv.org/abs/1403.6652">[arxiv]</a> <a
|
||
href="https://github.com/phanein/deepwalk">[Python]</a> <a
|
||
href="https://github.com/xgfs/deepwalk-c">[C++]</a></li>
|
||
</ul></li>
|
||
<li><strong>GEM</strong>
|
||
<ul>
|
||
<li>Graph Embedding Techniques, Applications, and Performance: A
|
||
Survey</li>
|
||
<li><a href="https://arxiv.org/abs/1705.02801">[arxiv]</a> <a
|
||
href="https://github.com/palash1992/GEM">[Python]</a></li>
|
||
</ul></li>
|
||
<li><strong>DNE-SBP</strong>
|
||
<ul>
|
||
<li>Deep Network Embedding for Graph Representation Learning in Signed
|
||
Networks</li>
|
||
<li><a href="https://ieeexplore.ieee.org/document/8486671">[paper]</a>
|
||
<a
|
||
href="https://github.com/shenxiaocam/Deep-network-embedding-for-graph-representation-learning-in-signed-networks">[Code]</a></li>
|
||
</ul></li>
|
||
</ul>
|
||
<h1 id="paper-references">Paper References</h1>
|
||
<p><a href="https://arxiv.org/abs/1901.00596">A Comprehensive Survey on
|
||
Graph Neural Networks</a>, arxiv’19</p>
|
||
<p><a href="https://arxiv.org/pdf/1806.08804.pdf">Hierarchical Graph
|
||
Representation Learning with Differentiable Pooling</a>, NIPS’18</p>
|
||
<p><strong>SEMAC</strong>, <a
|
||
href="https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16442">Link
|
||
Prediction via Subgraph Embedding-Based Convex Matrix Completion</a>,
|
||
AAAI 2018, <a
|
||
href="https://www.slideshare.net/gdm3003/semac-graph-node-embeddings-for-link-prediction">Slides</a></p>
|
||
<p><strong>MILE</strong>, <a
|
||
href="https://arxiv.org/pdf/1802.09612.pdf">MILE: A Multi-Level
|
||
Framework for Scalable Graph Embedding</a>, arxiv’18</p>
|
||
<p><strong>MetaGraph2Vec</strong>, <a
|
||
href="https://arxiv.org/abs/1803.02533">MetaGraph2Vec: Complex Semantic
|
||
Path Augmented Heterogeneous Network Embedding</a></p>
|
||
<p><strong>PinSAGE</strong>, <a
|
||
href="https://arxiv.org/abs/1806.01973">Graph Convolutional Neural
|
||
Networks for Web-Scale Recommender Systems</a></p>
|
||
<p><a href="https://dl.acm.org/citation.cfm?id=3159711">Curriculum
|
||
Learning for Heterogeneous Star Network Embedding via Deep Reinforcement
|
||
Learning</a>, WSDM ’18</p>
|
||
<p><a href="https://arxiv.org/abs/1711.07838">Adversarial Network
|
||
Embedding</a>, arxiv</p>
|
||
<p><strong>Role2Vec</strong>, <a
|
||
href="https://arxiv.org/abs/1802.02896">Learning Role-based Graph
|
||
Embeddings</a></p>
|
||
<p><strong>edge2vec</strong>, <a
|
||
href="https://arxiv.org/abs/1804.06111">Feature Propagation on Graph: A
|
||
New Perspective to Graph Representation Learning</a></p>
|
||
<p><strong>MINES</strong>, <a
|
||
href="http://cse.msu.edu/~mayao4/downloads/Multidimensional_Network_Embedding_with_Hierarchical_Structure.pdf">Multi-Dimensional
|
||
Network Embedding with Hierarchical Structure</a></p>
|
||
<p><a href="https://arxiv.org/abs/1804.05837">Walk-Steered Convolution
|
||
for Graph Classification</a></p>
|
||
<p><a href="https://arxiv.org/abs/1704.08829">Deep Feature Learning for
|
||
Graphs</a>, arxiv’17</p>
|
||
<p><a href="https://arxiv.org/abs/1710.10881">Fast Linear Model for
|
||
Knowledge Graph Embeddings</a>, arxiv’17</p>
|
||
<p><a href="https://arxiv.org/abs/1710.02971">Network Embedding as
|
||
Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec</a>,
|
||
arxiv’17</p>
|
||
<p><a href="https://arxiv.org/abs/1709.07604">A Comprehensive Survey of
|
||
Graph Embedding: Problems, Techniques and Applications</a>, arxiv’17</p>
|
||
<p><a href="https://arxiv.org/pdf/1709.05584.pdf">Representation
|
||
Learning on Graphs: Methods and Applications</a>, IEEE DEB’17</p>
|
||
<p><strong>CONE</strong>, <a
|
||
href="https://arxiv.org/abs/1709.01554">CONE: Community Oriented Network
|
||
Embedding</a>, arxiv’17</p>
|
||
<p><strong>LANE</strong>, <a
|
||
href="http://dl.acm.org/citation.cfm?id=3018667">Label Informed
|
||
Attributed Network Embedding</a>, WSDM’17</p>
|
||
<p><strong>Graph2Gauss</strong>, <a
|
||
href="https://arxiv.org/abs/1707.03815">Deep Gaussian Embedding of
|
||
Attributed Graphs: Unsupervised Inductive Learning via Ranking</a>,
|
||
arxiv <a
|
||
href="https://twitter.com/abojchevski/status/885502050133585925">[Bonus
|
||
Animation]</a></p>
|
||
<p><a
|
||
href="https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14696">Scalable
|
||
Graph Embedding for Asymmetric Proximity</a>, AAAI’17</p>
|
||
<p><a href="http://dl.acm.org/citation.cfm?id=2959169">Query-based Music
|
||
Recommendations via Preference Embedding</a>, RecSys’16</p>
|
||
<p><a href="http://dl.acm.org/citation.cfm?id=3060886">Tri-party deep
|
||
network representation</a>, IJCAI’16</p>
|
||
<p><a href="http://dl.acm.org/citation.cfm?id=2783296">Heterogeneous
|
||
Network Embedding via Deep Architectures</a>, KDD’15</p>
|
||
<p><a href="http://dl.acm.org/citation.cfm?id=2969070">Neural Word
|
||
Embedding As Implicit Matrix Factorization</a>, NIPS’14</p>
|
||
<p><a href="http://dl.acm.org/citation.cfm?id=2488393">Distributed
|
||
large-scale natural graph factorization</a>, WWW’13</p>
|
||
<p><a href="https://arxiv.org/abs/1610.09950">From Node Embedding To
|
||
Community Embedding</a>, arxiv</p>
|
||
<p><a href="https://arxiv.org/abs/1605.02115">Walklets: Multiscale Graph
|
||
Embeddings for Interpretable Network Classification</a>, arxiv</p>
|
||
<p><a href="https://arxiv.org/abs/1501.00358">Comprehend DeepWalk as
|
||
Matrix Factorization</a>, arxiv</p>
|
||
<h1 id="conference-workshop">Conference & Workshop</h1>
|
||
<p><a href="https://github.com/svjan5/GNNs-for-NLP">Graph Neural
|
||
Networks for Natural Language Processing</a>,
|
||
<strong>EMNLP’19</strong></p>
|
||
<p><a href="https://github.com/cnclabs/smore">SMORe : Modularize Graph
|
||
Embedding for Recommendation</a>, <strong>RecSys’19</strong></p>
|
||
<p><a href="http://www.mlgworkshop.org/2017/">13th International
|
||
Workshop on Mining and Learning with Graphs</a>,
|
||
<strong>MLG’17</strong></p>
|
||
<p><a href="http://snap.stanford.edu/proj/embeddings-www/">WWW-18
|
||
Tutorial Representation Learning on Networks</a>,
|
||
<strong>WWW’18</strong></p>
|
||
<h1 id="related-list">Related List</h1>
|
||
<p><a
|
||
href="https://github.com/benedekrozemberczki/awesome-graph-classification">awesome-graph-classification</a></p>
|
||
<p><a
|
||
href="https://github.com/benedekrozemberczki/awesome-community-detection">awesome-community-detection</a></p>
|
||
<p><a
|
||
href="https://github.com/Hironsan/awesome-embedding-models">awesome-embedding-models</a></p>
|
||
<p><a href="https://github.com/thunlp/NRLPapers">Must-read papers on
|
||
network representation learning (NRL) / network embedding (NE)</a></p>
|
||
<p><a href="https://github.com/thunlp/KRLPapers">Must-read papers on
|
||
knowledge representation learning (KRL) / knowledge embedding
|
||
(KE)</a></p>
|
||
<p><a
|
||
href="https://github.com/nate-russell/Network-Embedding-Resources">Network
|
||
Embedding Resources</a></p>
|
||
<p><a
|
||
href="https://github.com/Hironsan/awesome-embedding-models">awesome-embedding-models</a></p>
|
||
<p><a href="https://github.com/MaxwellRebo/awesome-2vec">2vec-type
|
||
embedding models</a></p>
|
||
<p><a href="https://github.com/thunlp/GNNPapers">Must-read papers on
|
||
GNN</a></p>
|
||
<p><a
|
||
href="https://github.com/DeepGraphLearning/LiteratureDL4Graph">LiteratureDL4Graph</a></p>
|
||
<p><a
|
||
href="https://github.com/benedekrozemberczki/awesome-graph-classification">awesome-graph-classification</a></p>
|
||
<h1 id="related-project">Related Project</h1>
|
||
<p><strong>Stanford Network Analysis Project</strong> <a
|
||
href="http://snap.stanford.edu/">website</a></p>
|
||
<p><strong>StellarGraph Machine Learning Library</strong> <a
|
||
href="https://www.stellargraph.io">website</a> <a
|
||
href="https://github.com/stellargraph/stellargraph">GitHub</a></p>
|
||
<p><a
|
||
href="https://github.com/chihming/awesome-network-embedding">networkembedding.md
|
||
Github</a></p>
|