deepgraphlearning / literaturedl4graph Goto Github PK

Hi,

Could you please add our ACL 2019 Workshop paper into the list? In our paper, we propose an end-to-end coreference resolver by combining pre-trained BERT with Relational Graph Convolutional Network (R-GCN).

You could find the paper here: https://arxiv.org/abs/1905.08868, and codes here: https://github.com/ianycxu/RGCN-with-BERT

Best regards,
Yinchuan

Hi,

Thank you very much for preparing this nice repo for graph related resources.

Could you please add our Bayesian-GCN [AAAI 2019] paper into the list? Essentially, we build on top of the GCN idea with topology exploration during the training.

Here's the info:
"Bayesian graph convolutional neural networks for semi-supervised classification"
Yingxue Zhang, Soumyasundar Pal, Mark Coates, Deniz Üstebay.

thank you,
Yingxue

Thanks for the repo, super-useful pointers!

We have been working on AmpliGraph,- a TensorFlow-based library for knowledge graph embeddings. Will you please add it to the list, under "Graph Representation Learning Systems"?

`AmpliGraph
<https://github.com/Accenture/AmpliGraph>`_
    | :author:`Luca Costabello, Sumit Pai, Chan Le Van, Rory McGrath, Nicholas McCarthy, Pedro Tabacof`

ANRL: Attributed Network Representation Learning via Deep Neural Networks is IJCAL2018 not AAAI2018

Great work on the compilation of this incredibly useful resource! I notice that Section 6 on Visualization looks rather short. May I suggest adding our paper? TLDR: We propose a method for visualizing graph data by the minimization of the t-SNE loss with GCNs.

GraphTSNE: A Visualization Technique for Graph-Structured Data
Yao Yang Leow, Thomas Laurent, Xavier Bresson
ICLR 2019 Workshop
https://github.com/leowyy/GraphTSNE

Detecting drug-drug interactions using artificial neural networks and classic graph similarity measures <https://arxiv.org/pdf/1903.04571.pdf>_
| :author:Shtar, Guy, Lior Rokach, and Bracha Shapira
| :venue:arXiv preprint arXiv:1903.04571 (2019)

PGCN: Disease gene prioritization by disease and gene embedding through graph convolutional neural networks <https://www.biorxiv.org/content/biorxiv/early/2019/01/28/532226.full.pdf>_
| :author:Li, Yu, et al
| :venue:bioRxiv (2019)

Identifying Protein-Protein Interaction using Tree LSTM and Structured Attention <https://ieeexplore.ieee.org/abstract/document/8665584>_
| :author:Ahmed, Mahtab, et al
| :venue:2019 IEEE 13th International Conference on Semantic Computing (ICSC). IEEE, 2019

Thanks for the great collection!!

We would like to bring to your attention our ICLR 2020 paper "GraphSAINT: Graph Sampling Based Inductive Learning Method". We propose a new minibatch training framework for general GNN models (e.g., GraphSAGE, GAT, JK-Net, MixHop, etc), which significantly improves the training efficiency and quality for large graphs and deep models.

Our code is also available at https://github.com/GraphSAINT/GraphSAINT

Thanks for your consideration.

Hi,

Thanks a lot for making this great resource :)!

Could you please add our SIGGRAPH 2019 paper to the list?
Here's the info:

MeshCNN: A Network with an Edge
Rana Hanocka, Amir Hertz, Noa Fish, Raja Giryes, Shachar Fleishman, Daniel Cohen-Or
SIGGRAPH 2019
Project Page

Hi!

Thank you for your incredible repository!

Could you please add the following paper under "Node Representation Learning in Dynamic Graphs", "Node Representation Learning in Heterogeneous Graphs", and "Unsupervised Node Representation Learning"? It is an oral paper in the research track at SIGKDD 2019 and lies at the intersection of all three topics!

Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks.
Srijan Kumar, Xikun Zhang, Jure Leskovec
25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2019.

Project website with new datasets and code: http://snap.stanford.edu/jodie