BLue1881euLB/Research-Line

A paper list of my research line, welcome to discuss with me.

Awesome paper list

A collection of graph embedding, deep learning, recommendation, knowledge graph, heterogeneous graph papers with reference implementations

Table of Contents

1. Recomendation
2. Graph
3. Bayesian Deep Learning
4. Datasets

Recomendation

Title	Conference	Author	Attachment
Large Scale Recommendation
Dynamic Attention Deep Model for Article Recommendation by Learning Human Editors’ Demonstration	KDD 2017	Xuejian Wang, Lantao Yu, Kan Ren
DKN: Deep Knowledge-Aware Network for News Recommendation	WWW 2018	Hongwei Wang, Fuzheng Zhang, Xing Xie, Minyi Guo	Tensorflow
Deep Interest Network for Click-Through Rate Prediction	KDD 2018	Guorui Zhou, Kun Gai, et al	Tensorflow
Normal
Learning Consumer and Producer Embeddings for User-Generated Content Recommendation	Recsys 2018	Wang-Cheng Kang, Julian McAuley
Spectral Collaborative Filtering	Recsys 2018	Lei Zheng, Chun-Ta, Philip S. Yu
Music Recommendation by Unified Hypergraph : Combining Social Media Information and Music Content	MM 2010	Bu Jiajun, Tan Shulong, Xiaofei He
News Recommendation
News Recommendation via Hypergraph Learning: Encapsulation of User Behavior and News Content	WSDM 2013	Lei Li, Tao Li
Weave & Rec : A Word Embedding based 3-D Convolutional Network for News Recommendation	CIKM 2018		Keras
Review Based Recommendation
A3NCF: An Adaptive Aspect Attention Model for Rating Prediction	IJCAI 2018	Zhiyong Cheng, Ying Ding, Xiangnan He, Lei Zhu, Xuemeng Song, Mohan Kankanhalli	Keras

Explainable

• Explainable Reasoning over Knowledge Graphs for Recommendation

• Explainable Recommendation Through Attentive Multi-View Learning (AAAI 2018)

• RippleNet : Propagating User Preferences on the Knowledge Graph for Recommender Systems (CIKM 2018)

• Min Zhang website (aim at explainable recommender system)

Graph

Title	Conference	Author	Attachment
Survey
Survey: Representation Learning on Graphs: Methods and Applications		William L. Hamilton, Rex Ying, Jure Leskovec
A Comprehensive Survey on Graph Neural Networks		Zonghan Wu ,Philip S. Yu
Graph Theory
SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS	ICLR 2017	Thomas N. Kipf, Max Welling	Tensorflow
GraphSAGE: Inductive Representation Learning on Large Graphs	NIPS 2017		Code
HOW POWERFUL ARE GRAPH NEURAL NETWORKS	ICLR 2019	Keyulu Xu, Weihua Hu, Jure Leskovec, Stefanie Jegelka
LanczosNet: Multi-Scale Deep Graph Convolutional Networks	ICLR 2019	Renjie Liao, et al	code
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations	NIPS 2018	Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan Salakhutdinov, Yann LeCun
Pitfalls of Graph Neural Network Evaluation	NIPS 2018	Shchur Oleksandr et al	Tensorflow & gnn bench mark
Hierarchical Graph Representation Learning with Differentiable Pooling	NIPS 2018	Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec	Code
Graph Attention Networks	ICLR 2018	Petar Veliˇckovi´, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li`, Yoshua Bengio	Tensorflow
Graph Application
Graph Convolutional Matrix Completion	KDD 2018	Rianne van den Berg, Thomas N. Kipf, Max Welling	Tensorflow
Modeling Relational Data with Graph Convolutional Networks	ESWC 2018	Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling	Keras,Tensorflow
PinSage: Graph Convolutional Neural Networks for Web-Scale Recommender Systems	KDD 2018	Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L. Hamilton, Jure Leskovec
Knowledge Graph
Translating Embeddings for Modeling Multi-relational Data	NIPS 2013	Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko	Code for TransE, TransH, TransR and PTransE
SimplE Embedding for Link Prediction in Knowledge Graphs	NIPS 2018	Seyed Mehran Kazemi, David Poole	Tensorflow
RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems	CIKM 2018	Hongwei Wang, Fuzheng Zhang, Jialin Wang, Miao Zhao, Wenjie Li, Xing Xie, Minyi Guo	Tensorflow
DKN: Deep Knowledge-Aware Network for News Recommendation	WWW 2018	Hongwei Wang, Fuzheng Zhang, Xing Xie, Minyi Guo	Tensorflow
Convolutional 2D Knowledge Graph Embeddings	AAAI 2017	Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel	Pytorch
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion	AAAI2019		Pytorch
HyperGraph
Hypergraph Neural Networks	AAAI 2019	Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji, Yue Gao	Pytorch
Structural Deep Embedding for Hyper-Networks	AAAI 2018	Ke Tu, Peng Cui, Xiao Wang, Fei Wang, Wenwu Zhu	Tensorflow
Modeling Multi-way Relations with Hypergraph Embedding	CIKM 2018	Chia-An Yu, Ching-Lun Tai, Tak-Shing Chan, Yi-Hsuan Yang	matlab
Heterogeneous Information Network
Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks	KDD 2017	[Huan Zhao], anming Yao, Jianda Li, Yangqiu Song and Dik Lun Lee	Python
Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model	KDD 2018	Binbin Hu, Chuan Shi, Wayne Xin Zhao, [Philip S. Yu]	Tensorflow&Keras,Data
Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks	IJCAI 2018	Xiaotian Han, Chuan Shi, Senzhang Wang, [Philip S. Yu], Li Song	Tensorflow
Deep Collective Classification in Heterogeneous Information Networks	WWW 2018		Keras
Are Meta-Paths Necessary ? Revisiting Heterogeneous Graph Embeddings	CIKM 2018	Rana Hussein	Request in email
PME : Projected Metric Embedding on Heterogeneous Networks for Link Prediction	KDD 2018	Hongxu Chen et al	Request in email
metapath2vec: Scalable Representation Learning for Heterogeneous Networks	KDD 2017	Yuxiao Dong	C++
Relation Structure-Aware Heterogeneous Information Network Embedding	AAAI 2019	Yuanfu Lu, Chuan Shi, Linmei Hu, Zhiyuan Liu	Pytorch
Hyperbolic embedding
Poincaré Embeddings for Learning Hierarchical Representations	NIPS 2017	Maximilian Nickel, Kiela Douwe	Pytorch
Hyperbolic Neural Networks	NIPS 2018	Octavian Eugen Ganea, Hofmann, Thomas	Tensorflow

• Exploiting Relational Information in Social Networks using Geometric Deep Learning on Hypergraphs

  other implement resource:

  • gated-graph-neural-network-samples
  • Graph-neural-networks jupyter tutorial
  • Deep Graph Library (DGL) Python package
  • gnn-benchmark
  • pytorch_geometric
  • graph literature

  Other reading materials:

  • Tsinghua University Graph papers reading list

BayesianDeepLearning

Title	Conference	Author	Attachment
Survey
Recent Advances in Autoencoder-Based Representation Learning	NIPS 2018	Michael Tschannen, Olivier Bachem, Mario Lucic

Datasets

homegenerous graph dataset

• PubMed Diabetes

  • The Pubmed Diabetes dataset consists of 19717 scientific publications from PubMed database pertaining to diabetes classified into one of three classes. The citation network consists of 44338 links. Each publication in the dataset is described by a TF/IDF weighted word vector from a dictionary which consists of 500 unique words. The README file in the dataset provides more details.
  • Download Link:
    • https://linqs-data.soe.ucsc.edu/public/Pubmed-Diabetes.tgz
  • Related Papers:
    • Galileo Namata, et. al. "Query-driven Active Surveying for Collective Classification." MLG. 2012.

• Cora

  • The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words. The README file in the dataset provides more details.
  • Download Link:
    • https://linqs-data.soe.ucsc.edu/public/lbc/cora.tgz
  • Related Papers:
    • Qing Lu, and Lise Getoor. "Link-based classification." ICML, 2003.
    • Prithviraj Sen, et al. "Collective classification in network data." AI Magazine, 2008.

other useful datasets link:

• citation dataset
  • https://linqs.soe.ucsc.edu/data

heteregeneous graph datasets

• IMDB Datasets
  • MovieLens Latest Dataset which consists of 33,000 movies. And it contains four types of nodes: movie, director, actor and actress, connected by two types of relations/link: directed link and actor/actress staring link. Each movie is assigned with a set of class labels, indicating generes of the movie. For each movie, we extract a bag of words vector of all the plot summary about the movie as local features, which include 1000 words.
  • Download Link:
    • https://github.com/trangptm/Column_networks/tree/master/data
  • Related Papers:
    • T. Pham, et al. "Column networks for collective classification." In AAAI, 2017.
    • Zhang, Yizhou et al. "Deep Collective Classification in Heterogeneous Information Networks" In WWW, 2018.

other useful dataset links

• processed Datasets
  • https://github.com/librahu/Heterogeneous-Information-Network-Datasets-for-Recommendation-and-Network-Embedding/blob/master/README.md