ICLR2023图神经网络相关的文章整理

  1. Graph Attention Retrospective Kimon Fountoulakis (Waterloo)

  2. Limitless Stability for Graph Convolutional Networks

  3. The Graph Learning Attention Mechanism: Learnable Sparsification Without Heuristics

  4. Network Controllability Perspectives on Graph Representation

  5. Graph Contrastive Learning Under Heterophily: Utilizing Graph Filters to Generate Graph Views

  6. Spectral Augmentation for Self-Supervised Learning on Graphs

  7. Simple and Deep Graph Attention Networks

  8. Agent-based Graph Neural Networks Karolis Martinkus (ETH), Pál András Papp (ETH), Benedikt Schesch (ETH) Roger Wattenhofer (ETH)

  9. A Class-Aware Representation Refinement Framework for Graph Classification Jiaxing Xu, Jinjie Ni, Sophi Shilpa Gururajapathy & Yiping Ke (NTU)

  10. ReD-GCN: Revisit the Depth of Graph Convolutional Network

  11. Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective

  12. Simple Spectral Graph Convolution from an Optimization Perspective

  13. GraphEditor: An Efficient Graph Representation Learning and Unlearning Approach Weilin Cong, Mehrdad Mahdavi (PSU)

  14. Specformer: Spectral Graph Neural Networks Meet Transformers

  15. DiGress: Discrete Denoising diffusion for graph generation Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan Cevher, Pascal Frossard (EPFL)

  16. ASGNN: Graph Neural Networks with Adaptive Structure

  17. DeepGRAND: Deep Graph Neural Diffusion

  18. Empowering Graph Representation Learning with Test-Time Graph Transformation

  19. The Impact of Neighborhood Distribution in Graph Convolutional Networks

  20. NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

  21. Wide Graph Neural Network

  22. How Powerful is Implicit Denoising in Graph Neural Networks Songtao Liu (PSU), Rex Ying (Yale), Hanze Dong (HKUST), Lu Lin (PSU), Jinghui Chen (PSU), Dinghao Wu (PSU)

  23. Learnable Graph Convolutional Attention Networks

  24. Revisiting Robustness in Graph Machine Learning

  25. Graph Neural Bandits Parnian Kassraie (ETH), Andreas Krause (ETH), Ilija Bogunovic (UCL)

  26. Learning Graph Neural Network Topologies

  27. Affinity-Aware Graph Networks Ameya Velingker (Google Research), Ali Kemal Sinop (Google Research), Ira Ktena (DeepMind), Petar Velickovic (DeepMind), Sreenivas Gollapudi (Google Research)

  28. Diffusing Graph Attention

  29. Relational Curriculum Learning for Graph Neural Networks

  30. Stable, Efficient, and Flexible Monotone Operator Implicit Graph Neural Networks

  31. Distributional Signals for Node Classification in Graph Neural Networks

  32. Rewiring with Positional Encodings for GNNs Rickard Bruel-Gabrielsson (MIT), Mikhail Yurochkin (MIT-IBM) Justin Solomon (MIT)

  33. Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency

  34. Fair Graph Message Passing with Transparency Zhimeng Jiang (TAMU), Xiaotian Han (TAMU), Chao Fan (TAMU), Zirui Liu (Rice), Na Zou (TAMU), Ali Mostafavi (TAMU), Xia Hu (Rice)

  35. Sign and Basis Invariant Networks for Spectral Graph Representation Learning Derek Lim (MIT), Joshua Robinson (MIT), Lingxiao Zhao (CMU), Tess Smidt (MIT), Suvrit Sra (MIT) Haggai Maron (NVIDIA Research) Stefanie Jegelka (MIT)

  36. Graph Neural Networks Are More Powerful Than We Think Charilaos I. Kanatsoulis, Alejandro Ribeiro (UPenn)

  37. Robust Graph Representation Learning via Predictive Coding

  38. Universal Graph Neural Networks without Message Passing

  39. Fair Attribute Completion on Graph with Missing Attributes

  40. Asynchronous Message Passing: A New Framework for Learning in GraphsLukas Faber, Roger Wattenhofer (ETH)

  41. Graph Neural Networks as Gradient Flows: understanding graph convolutions via energyFrancesco Di Giovanni, James Rowbottom, Benjamin P. Chamberlain, Thomas Markovich, Michael M. Bronstein (Twitter)

  42. Rethinking the Expressive Power of GNNs via Graph Biconnectivity

  • 3
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

刘大彪

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值