Addressing Aggregation-Induced Information Loss in Graph Neural Networks
Open Access
- 21 February 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1036-1046
Abstract
No abstract availableFunding Information
- the State Key Laboratory of General Artificial Intelligence (N\/A)
- The National Natural Science Foundation of China (62276006)
- The Humanities and Social Sciences Research Planning Fund Project of the Ministry of Education (23YJA880091)
This publication has 11 references indexed in Scilit:
- On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks2023
- Oversquashing in GNNs through the lens of information contraction and graph expansion2022
- Improving Graph Neural Network Expressivity via Subgraph Isomorphism CountingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Multi-Scale attributed node embeddingJournal of Complex Networks, 2021
- Weisfeiler and Leman Go Neural: Higher-Order Graph Neural NetworksProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised LearningProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Quantum chemistry structures and properties of 134 kilo moleculesScientific Data, 2014
- Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17Journal of Chemical Information and Modeling, 2012
- Automating the Construction of Internet Portals with Machine LearningInformation Retrieval Journal, 2000