thunlp / gnnpapers Goto Github PK

Thank you for your great effort in surveying these papers. We believe you might have missed two important papers from our lab.

M. Zhang, Z. Cui, M. Neumann, and Y. Chen, An End-to-End Deep Learning Architecture for Graph Classification, Proc. AAAI Conference on Artificial Intelligence (AAAI-18), 2018. This is the first paper to study advanced pooling layers for graph classification.

M. Zhang and Y. Chen, Link Prediction Based on Graph Neural Networks, Advances in Neural Information Processing Systems (NeurIPS-18), spotlight presentation, 2018. This is a successful GNN application in social networks and link prediction.

We would appreciate much if you can add them to the list. Thanks!

Hi there,
Thanks for your suggestions!

but I think maybe there should be eNsp, not eMsp in front of Explainability. (maybe line 21)

sincerely,

I found some unrelated papers in this list, such as:

Non-local Neural Networks. Wang, Xiaolong and Girshick, Ross and Gupta, Abhinav and He, Kaiming. CVPR 2018.

Neural Message Passing for Quantum Chemistry. Gilmer, Justin and Schoenholz, Samuel S and Riley, Patrick F and Vinyals, Oriol and Dahl, George E. 2017.

Hi, thanks for the great collection!

I would like to point out our recent works

• "Principal Neighbourhood Aggregation for Graph Nets". NeurIPS 2020 (paper, code)
• "Directional Graph Networks". Oral at DiffGeo4DL workshop NeurIPS 2020 (paper, code)

I think they would both fit perfectly in the analysis section.

Thank you very much!

We have some recent work that enables node-level privacy for training GNNs!
This was accepted as an Oral at PAIR2Struct, ICLR 2022:

"Node-Level Differentially Private Graph Neural Networks"
Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, and Prateek Jain.

URL: https://openreview.net/pdf?id=BCfgOLx3gb9

Our paper on scalable graph neural networks for dynamic graphs has been recently accepted by the top conference in the supercomputing/HPC area - named ‘ACM/IEEE Supercomputing 2021’. This is a joint work between the US and India team at IBM Research. The paper is available from the following link.
Efficient Scaling of Dynamic Graph Neural Networks
Venkatesan T. Chakaravarthy, Shivmaran S. Pandian, Saurabh Raje, Yogish Sabharwal, Toyotaro Suzumura, Shashanka Ubaru
Paper: https://lnkd.in/dzcPKtRX
Conference: SC'21 (https://sc21.supercomputing.org/)
It would be great if you could add this work to the Efficiency section. The code will be available soon.

Please add Graph neural network based coarse-grained mapping prediction paper under Chemistry and biology.

Here is the link to the paper: https://pubs.rsc.org/en/content/articlelanding/2020/SC/D0SC02458A#fn1

Graph neural network based coarse-grained mapping prediction Chem Sci 2020. paper

Zhiheng Li, Geemi P. Wellawatte, Maghesree Chakraborty, Heta A. Gandhi, Chenliang Xu, Andrew D. White.

Thanks!

Hi,

thank you for the great GNN paper collection!

I would like to point out our recent work:
Stierle, M., Weinzierl, S., Harl, M., Matzner, M.: A technique for determiningrelevance scores of process activities using graph-based neural networks. Decision Support Systems 144, 113511 (2021)

You can access the paper here

Thank you very much!
Sven

Great list! Feel free to add these two papers related to capsule networks.

1. Graph Capsule Convolutional Neural Networks. Saurabh Verma, Zhi-Li Zhang (ICML workshop 2018, our paper :))
2. Capsule Graph Neural Network Zhang. Xinyi, Lihui Chen (ICLR 2019)

We believe our interactive article published at Distill would be a valuable addition to the Survey section:

"Understanding Convolutions on Graphs", Distill, 2021.
Ameya Daigavane and Balaraman Ravindran and Gaurav Aggarwal.

URL: https://distill.pub/2021/understanding-gnns/

Thanks for the great collection!

I would like to point out our recent paper in ICLR 2020, "GraphSAINT: Graph sampling based inductive method". We proposed a graph sampling based minibatch training algorithm that works well on large graphs and deep GNNs. I think it fits under the "Efficiency" category of your collection.

Our code is available via https://github.com/GraphSAINT/GraphSAINT

The PyTorch Geometric library also has a reference implementation.

Hi,

Please consider adding these two papers to your list:

1. Understanding Attention and Generalization in Graph Neural Networks. Boris Knyazev, Graham W. Taylor, Mohamed R. Amer. 2019. https://arxiv.org/pdf/1905.02850.pdf

2. Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules. Boris Knyazev, Xiao Lin, Mohamed R. Amer, Graham W. Taylor. NIPS 2018 Workshop. https://arxiv.org/abs/1811.09595

this paper "Graph Neural Networks: A Review of Methods and Applications. arxiv 2018" should in 2019

Hi

Thx for keeping a good collection of GNN papers. I found it comprehensive and interesting!

Can I suggest a recent IJCAI2019 paper (also accepted for ICML workshop 2019) : Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph (https://arxiv.org/abs/1905.04042) for the addition of the list?

This paper shows an application of GNN on few-shot learning. It would be nice to add it in.

Organizing papers according to their contents is good, but chronological order makes it easier to follow the new trend in top conferences. We can put several markdown files in this repo, each named as "ICML", "NIPS" etc, and inside we have subsections like "2020", "2019", etc. I personally think it would be much more convenient.

Hi THUNLP:

Thanks a lot for the curated list! Here are three papers from NIPS this year, which maybe of interest to the audience. Thanks!

http://papers.nips.cc/paper/7729-hierarchical-graph-representation-learning-with-differentiable-pooling
http://papers.nips.cc/paper/8005-constrained-graph-variational-autoencoders-for-molecule-design
http://papers.nips.cc/paper/7877-graph-convolutional-policy-network-for-goal-directed-molecular-graph-generation

Best Regards,
Qi