Research map / Graph learning / GNN architectures
Beyond Coordinates: Encoding Graph Structure via Contextual Distribution and Relational Similarity
Feifei Qian, Lu Bai, Lixin Cui, Ming Li, Hangyuan Du, Bo Jiang, Lixiang Xu, Edwin Hancock
Read the paperCheck your idea against 137,217 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 a graph structure encoding approach based on contextual distribution and relational similarity to enhance MPNNs and Graph Transformers beyond 1-WL expressivity limits.
Problem
Standard MPNNs are bounded by the 1-WL test and Graph Transformers lack inductive bias for graph structure; existing structural enhancements rely on subgraph-based aggregation.
Approach
Encodes graph structure through contextual distributions and relational similarity between nodes rather than explicit coordinates or subgraph aggregation, as suggested by the title; full method details unavailable.
Closest papers by meaning
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 2025 · similarity 0.90)
- Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-Based Similarity (AAAI 2024 · similarity 0.90)
- Positional Encoding meets Persistent Homology on Graphs (ICML 2025 · similarity 0.90)
- GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning (ICML 2025 · similarity 0.89)
- Homomorphism Counts as Structural Encodings for Graph Learning (ICLR 2025 · similarity 0.89)
- Graph Positional and Structural Encoder (ICML 2024 · similarity 0.89)
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.
