Research map / Graph learning / Graph self-supervised learning
MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes MultiNet, an adaptive multi-viewed subgraph convolutional network that addresses graph-level over-smoothing to improve graph classification.
Problem
Over-smoothing in GCNs at the graph level, which degrades graph classification performance, whereas prior work focuses on node-level discriminability for node classification.
Approach
Explains graph-level over-smoothing and addresses it with adaptive multi-viewed subgraph convolutions, shifting focus from node-level representation discriminability to graph-level representations.
Experimental setup
Builds on: graph convolutional networks
Closest papers by meaning
- Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module (NeurIPS 2024 · similarity 0.90)
- Subgraph Invariant Learning Towards Large-Scale Graph Node Classification (AAAI 2025 · similarity 0.89)
- Learning Convolutional Neural Networks for Graphs (ICML 2016 · similarity 0.89)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (NeurIPS 2024 · similarity 0.88)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 2024 · similarity 0.88)
- Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.