Research map / Graph learning / Graph algorithms and clustering
Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding
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 direct proximity embedding instead of DeepWalk node embeddings (DWR) | ProxEmbed · LinkedIn and Facebook | NDCG/MAP | Helped |
| use learned path features instead of engineered meta-graph/meta-path features | ProxEmbed vs MGP/MPP · LinkedIn and Facebook | NDCG/MAP: e.g. +18.9% NDCG on LinkedIn-schoolmate | Helped |
| use ProxEmbed instead of SRW with only 10 training tuples | ProxEmbed · DBLP advisor/advisee | NDCG/MAP | Hurt |
| add path length discount (alpha 0 -> 0.1) (ablation) | ProxEmbed · six proximity classes, 100 training tuples | NDCG/MAP | Helped |
| increase path discount alpha to 10 (ablation) | ProxEmbed · six proximity classes, 100 training tuples | NDCG/MAP | Hurt |
| embedding dimension d = 64 (ablation) | ProxEmbed · six proximity classes | NDCG/MAP | Helped |
Closest papers by meaning
- Distance-Aware DAG Embedding for Proximity Search on Heterogeneous Graphs (AAAI 2018 · similarity 0.92)
- Scalable Graph Embedding for Asymmetric Proximity (AAAI 2017 · similarity 0.88)
- Learning Triple Embeddings from Knowledge Graphs (AAAI 2020 · similarity 0.87)
- GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding (ICLR 2020 · similarity 0.87)
- Conditional Network Embeddings (ICLR 2019 · similarity 0.87)
- Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation (ICML 2025 · similarity 0.85)
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.