Timezone: »
The success of graph neural networks (GNNs) largely relies on the process of aggregating information from neighbors defined by the input graph structures. Notably, message passing based GNNs, e.g., graph convolutional networks, leverage the immediate neighbors of each node during the aggregation process, and recently, graph diffusion convolution (GDC) is proposed to expand the propagation neighborhood by leveraging generalized graph diffusion. However, the neighborhood size in GDC is manually tuned for each graph by conducting grid search over the validation set, making its generalization practically limited. To address this issue, we propose the adaptive diffusion convolution (ADC) strategy to automatically learn the optimal neighborhood size from the data. Furthermore, we break the conventional assumption that all GNN layers and feature channels (dimensions) should use the same neighborhood for propagation. We design strategies to enable ADC to learn a dedicated propagation neighborhood for each GNN layer and each feature channel, making the GNN architecture fully coupled with graph structures---the unique property that differs GNNs from traditional neural networks. By directly plugging ADC into existing GNNs, we observe consistent and significant outperformance over both GDC and their vanilla versions across various datasets, demonstrating the improved model capacity brought by automatically learning unique neighborhood size per layer and per channel in GNNs.
Author Information
Jialin Zhao (Tsinghua University, Tsinghua University)
Yuxiao Dong (Tsinghua University)
Ming Ding (Tsinghua University)
Evgeny Kharlamov (University of Oslo, Norway)
Jie Tang (Tsinghua University)

Jie Tang is a WeBank Chair Professor of Computer Science at Tsinghua University. He is a Fellow of the ACM, a Fellow of AAAI, and a Fellow of IEEE. His interest is artificial general intelligence (AGI). His research received the SIGKDD Test-of-Time Award (10-year Best Paper). He also received the SIGKDD Service Award. Recently, he puts all efforts into Large Language Models (LLMs): GLM, ChatGLM, etc.
More from the Same Authors
-
2021 : A Large-Scale Database for Graph Representation Learning »
Scott Freitas · Yuxiao Dong · Joshua Neil · Duen Horng Chau -
2021 : Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning »
Qinkai Zheng · Xu Zou · Yuxiao Dong · Yukuo Cen · Da Yin · Jiarong Xu · YANG YANG · Jie Tang -
2021 : OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Hongyu Ren · Maho Nakata · Yuxiao Dong · Jure Leskovec -
2023 Poster: ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation »
Jiazheng Xu · Xiao Liu · Yuchen Wu · Yuxuan Tong · Qinkai Li · Ming Ding · Jie Tang · Yuxiao Dong -
2022 Poster: CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers »
Ming Ding · Wendi Zheng · Wenyi Hong · Jie Tang -
2021 : Invited talk 3 »
Jie Tang -
2021 Poster: CogView: Mastering Text-to-Image Generation via Transformers »
Ming Ding · Zhuoyi Yang · Wenyi Hong · Wendi Zheng · Chang Zhou · Da Yin · Junyang Lin · Xu Zou · Zhou Shao · Hongxia Yang · Jie Tang -
2021 : A Large-Scale Database for Graph Representation Learning »
Scott Freitas · Yuxiao Dong · Joshua Neil · Duen Horng Chau -
2021 Poster: UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis »
Zhu Zhang · Jianxin Ma · Chang Zhou · Rui Men · Zhikang Li · Ming Ding · Jie Tang · Jingren Zhou · Hongxia Yang -
2021 Poster: A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems »
Yi Ma · Xiaotian Hao · Jianye Hao · Jiawen Lu · Xing Liu · Tong Xialiang · Mingxuan Yuan · Zhigang Li · Jie Tang · Zhaopeng Meng -
2020 Poster: Open Graph Benchmark: Datasets for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Marinka Zitnik · Yuxiao Dong · Hongyu Ren · Bowen Liu · Michele Catasta · Jure Leskovec -
2020 Spotlight: Open Graph Benchmark: Datasets for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Marinka Zitnik · Yuxiao Dong · Hongyu Ren · Bowen Liu · Michele Catasta · Jure Leskovec -
2020 Poster: Graph Random Neural Networks for Semi-Supervised Learning on Graphs »
Wenzheng Feng · Jie Zhang · Yuxiao Dong · Yu Han · Huanbo Luan · Qian Xu · Qiang Yang · Evgeny Kharlamov · Jie Tang -
2020 Oral: Graph Random Neural Networks for Semi-Supervised Learning on Graphs »
Wenzheng Feng · Jie Zhang · Yuxiao Dong · Yu Han · Huanbo Luan · Qian Xu · Qiang Yang · Evgeny Kharlamov · Jie Tang -
2020 Poster: A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices »
Jiezhong Qiu · Chi Wang · Ben Liao · Richard Peng · Jie Tang -
2020 Poster: CogLTX: Applying BERT to Long Texts »
Ming Ding · Chang Zhou · Hongxia Yang · Jie Tang -
2018 Poster: Bandit Learning with Implicit Feedback »
Yi Qi · Qingyun Wu · Hongning Wang · Jie Tang · Maosong Sun