A critical look at the evaluation of GNNs under heterophily: Are we really making progress?

22 February 2023

Oleg Platonov

Denis Kuznedelev

Michael Diskin

Artem Babenko

Liudmila Prokhorenkova

ArXiv PDF HTML

Papers citing "A critical look at the evaluation of GNNs under heterophily: Are we really making progress?"

38 / 138 papers shown

Title
Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification Henan Sun Xunkai Li Zhengyu Wu Daohan Su Ronghua Li Guoren Wang 27 12 0 07 Dec 2023
Mixture of Weak & Strong Experts on Graphs Hanqing Zeng Hanjia Lyu Diyi Hu Yinglong Xia Jiebo Luo 23 3 0 09 Nov 2023
Simple and Asymmetric Graph Contrastive Learning without Augmentations Teng Xiao Huaisheng Zhu Zhengyu Chen Suhang Wang 22 31 0 29 Oct 2023
Are GATs Out of Balance? Nimrah Mustafa Aleksandar Bojchevski R. Burkholz 41 4 0 11 Oct 2023
How Graph Neural Networks Learn: Lessons from Training Dynamics Chenxiao Yang Qitian Wu David Wipf Ruoyu Sun Junchi Yan AI4CE GNN 14 1 0 08 Oct 2023
HoloNets: Spectral Convolutions do extend to Directed Graphs Christian Koke Daniel Cremers 31 8 0 03 Oct 2023
FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations C. Ekbote Ajinkya Deshpande Arun Shankar Iyer Ramakrishna Bairi Sundararajan Sellamanickam SSL 39 3 0 03 Oct 2023
Cooperative Graph Neural Networks Ben Finkelshtein Xingyue Huang Michael M. Bronstein .Ismail .Ilkan Ceylan GNN 22 19 0 02 Oct 2023
Geometric instability of graph neural networks on large graphs Emily L Morris Haotian Shen Weiling Du Muhammad Hamza Sajjad Borun Shi GNN 22 0 0 19 Aug 2023
Investigating the Interplay between Features and Structures in Graph Learning Daniele Castellana Federico Errica 15 3 0 18 Aug 2023
Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions Lukas Gosch Simon Geisler Daniel Sturm Bertrand Charpentier Daniel Zügner Stephan Günnemann AAML GNN 6 26 0 27 Jun 2023
PathMLP: Smooth Path Towards High-order Homophily Chenxuan Xie Jiajun Zhou Sheng Gong Jiacheng Wan Jiaxu Qian Shanqing Yu Qi Xuan Xiaoniu Yang 11 5 0 23 Jun 2023
Evolving Computation Graphs Andreea Deac Jian Tang 14 1 0 22 Jun 2023
GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection Jianheng Tang Fengrui Hua Zi-Chao Gao P. Zhao Jia Li 14 53 0 21 Jun 2023
SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations Qitian Wu Wen-Long Zhao Chenxiao Yang Hengrui Zhang Fan Nie Haitian Jiang Yatao Bian Junchi Yan AI4CE 33 74 0 19 Jun 2023
OpenGSL: A Comprehensive Benchmark for Graph Structure Learning Zhiyao Zhou Sheng Zhou Bochao Mao Xu Zhou Jiawei Chen Qiaoyu Tan Daochen Zha Yan Feng Chun-Yen Chen C. Wang 27 20 0 17 Jun 2023
A Simple and Scalable Graph Neural Network for Large Directed Graphs Seiji Maekawa Yuya Sasaki Makoto Onizuka GNN 6 0 0 14 Jun 2023
On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks Donald Loveland Jiong Zhu Mark Heimann Benjamin Fish Michael T. Shaub Danai Koutra 23 5 0 08 Jun 2023
Towards Deep Attention in Graph Neural Networks: Problems and Remedies Soo Yong Lee Fanchen Bu Jaemin Yoo Kijung Shin GNN 9 30 0 04 Jun 2023
Clarify Confused Nodes via Separated Learning Jiajun Zhou Sheng Gong Chenxuan Xie Shanqing Yu Qi Xuan Xiaoniu Yang Xiaoniu Yang 47 3 0 04 Jun 2023
Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? Haitao Mao Zhikai Chen Wei Jin Haoyu Han Yao Ma Tong Zhao Neil Shah Jiliang Tang 21 31 0 02 Jun 2023
Is Rewiring Actually Helpful in Graph Neural Networks? Domenico Tortorella A. Micheli AI4CE 27 2 0 31 May 2023
Graph Neural Convection-Diffusion with Heterophily Kai Zhao Qiyu Kang Yang Song Rui She Sijie Wang Wee Peng Tay 22 27 0 26 May 2023
A Fractional Graph Laplacian Approach to Oversmoothing Sohir Maskey Raffaele Paolino Aras Bacho Gitta Kutyniok 22 27 0 22 May 2023
Edge Directionality Improves Learning on Heterophilic Graphs Emanuele Rossi Bertrand Charpentier Francesco Di Giovanni Fabrizio Frasca Stephan Günnemann Michael M. Bronstein 15 56 0 17 May 2023
GCNH: A Simple Method For Representation Learning On Heterophilous Graphs Andrea Cavallo Claas Grohnfeldt Michele Russo Giulio Lovisotto L. Vassio 15 10 0 21 Apr 2023
Graph Contrastive Learning under Heterophily via Graph Filters Wenhan Yang Baharan Mirzasoleiman 12 2 0 11 Mar 2023
Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts Gleb Bazhenov Denis Kuznedelev A. Malinin Artem Babenko Liudmila Prokhorenkova OOD 6 3 0 27 Feb 2023
Diffusion Probabilistic Models for Structured Node Classification Hyosoon Jang Seonghyun Park Sangwoo Mo Sungsoo Ahn DiffM 14 3 0 21 Feb 2023
Attending to Graph Transformers Luis Muller Mikhail Galkin Christopher Morris Ladislav Rampášek 44 84 0 08 Feb 2023
Neighborhood Homophily-based Graph Convolutional Network Sheng Gong Jiajun Zhou Chenxuan Xie Qi Xuan GNN 18 7 0 24 Jan 2023
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond Oleg Platonov Denis Kuznedelev Artem Babenko Liudmila Prokhorenkova 51 37 0 13 Sep 2022
Understanding convolution on graphs via energies Francesco Di Giovanni J. Rowbottom B. Chamberlain Thomas Markovich Michael M. Bronstein GNN 18 42 0 22 Jun 2022
How Powerful are Spectral Graph Neural Networks Xiyuan Wang Muhan Zhang 70 175 0 23 May 2022
Graph Neural Networks for Graphs with Heterophily: A Survey Xin-Yang Zheng Yi Wang Yixin Liu Ming Li Miao Zhang Di Jin Philip S. Yu Shirui Pan 19 213 0 14 Feb 2022
Beyond Low-frequency Information in Graph Convolutional Networks Deyu Bo Xiao Wang C. Shi Huawei Shen GNN 87 554 0 04 Jan 2021
Geom-GCN: Geometric Graph Convolutional Networks Hongbin Pei Bingzhen Wei Kevin Chen-Chuan Chang Yu Lei Bo Yang GNN 167 1,058 0 13 Feb 2020
Multi-scale Attributed Node Embedding Benedek Rozemberczki Carl Allen Rik Sarkar GNN 145 828 0 28 Sep 2019