Research map / Reinforcement learning / Visual and representation RL
Reinforcement Learning Based Meta-Path Discovery in Large-Scale Heterogeneous Information Networks
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 |
|---|---|---|---|
| add type context representation module (average of type vectors) instead of trainable object embeddings (ablation) | MPDRL · reasoning success ratio during training | success ratio | Helped |
| use MPDRL-discovered meta-paths instead of baselines (HeteSim, FSPG, PCRW, AutoPath, DeepWalk, Metapath2vec, DeepPath) | link prediction classifier · six relations on Yago and NELL | AUC | Helped |
| increase reward factor gamma (ablation) | MPDRL · average reasoning path length | path length | Helped |
| reduce reward factor below 0.8 (ablation) | MPDRL · training speed | convergence | Hurt |
| use embedding-based methods (DeepWalk) on complex HIN | DeepWalk · link prediction | AUC | Hurt |
Closest papers by meaning
- Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs (NeurIPS 2025 · similarity 0.87)
- GraphMSE: Efficient Meta-path Selection in Semantically Aligned Feature Space for Graph Neural Networks (AAAI 2021 · similarity 0.87)
- Long-range Meta-path Search on Large-scale Heterogeneous Graphs (NeurIPS 2024 · similarity 0.86)
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning (ICLR 2018 · similarity 0.85)
- Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks (AAAI 2023 · similarity 0.84)
- Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation (ICML 2025 · similarity 0.83)
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.