Research map / Graph learning / Knowledge and temporal graphs
A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use A*Net with neural-priority node and edge selection | Path-based knowledge graph reasoning · ogbl-wikikg2 | MRR (Test): 0.6392 -> 0.6767 | Helped |
| Use A*Net with sparse propagation instead of full-graph propagation | Knowledge graph reasoning · FB15k-237 | messages per step: 544,230 -> 38,610 | Helped |
| Use A*Net with sparse propagation instead of full-graph propagation | Knowledge graph reasoning · WN18RR | time per epoch: 9.42 min -> 1.39 min | Helped |
| Use A*Net instead of NBFNet | Knowledge graph reasoning · FB15k-237 transductive | MRR: 0.415 -> 0.411 | No clear effect |
| Use A*Net instead of NBFNet | Knowledge graph reasoning · WN18RR transductive | MRR: 0.551 -> 0.549 | No clear effect |
| Replace neural priority with PPR priority (ablation) | A*Net · FB15k-237 transductive | MRR: 0.411 -> 0.266 | Hurt |
| Replace neural priority with degree priority (ablation) | A*Net · FB15k-237 transductive | MRR: 0.411 -> 0.347 | Hurt |
| Replace neural priority with random priority (ablation) | A*Net · FB15k-237 transductive | MRR: 0.411 -> 0.378 | Hurt |
| Share weights between the priority function and reasoning predictor (ablation) | A*Net · FB15k-237 transductive | MRR: 0.374 -> 0.411 | Helped |
| Reduce node ratio to 1% or degree ratio to 10% (ablation) | A*Net · FB15k-237 | speedup versus NBFNet: 8.7× | Helped |
Closest papers by meaning
- KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning (ICML 2024 · similarity 0.90)
- Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs (NeurIPS 2025 · similarity 0.89)
- Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models (ICML 2025 · similarity 0.89)
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (ICLR 2024 · similarity 0.89)
- Talk like a Graph: Encoding Graphs for Large Language Models (ICLR 2024 · similarity 0.89)
- DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion (NeurIPS 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.