Research map / Graph learning / Graph algorithms and clustering
Distance-Aware DAG Embedding for Proximity Search on Heterogeneous 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 |
|---|---|---|---|
| add distance discount beta across DAGs (ablation) | D2AGE · Facebook classmate | NDCG@10: 0.374 -> 0.856 | Helped |
| add distance discount beta across DAGs (ablation) | D2AGE · Linkedin schoolmate | NDCG@10: 0.658 -> 0.678 | Helped |
| add distance discount alpha within DAG (ablation) | D2AGE · Facebook classmate | NDCG@10: 0.824 -> 0.856 | Helped |
| add distance discount alpha within DAG (ablation) | D2AGE · DBLP advisee | NDCG@10: 0.405 -> 0.417 | Helped |
| add both distance discounts (vs DAG-LSTM-like with max pooling) (ablation) | D2AGE · Facebook classmate | NDCG@10: 0.362 -> 0.856 | Helped |
| use DAG structure without alpha discount instead of paths (ProxEmbed) (ablation) | D2AGE · Linkedin schoolmate | NDCG@10: 0.652 -> 0.669 | Mixed |
| use full D2AGE (DAG + distance awareness) instead of path-based ProxEmbed | D2AGE vs ProxEmbed · DBLP advisor | NDCG@10: 0.765 -> 0.779 | Helped |
| use full D2AGE instead of ProxEmbed | D2AGE vs ProxEmbed · Facebook classmate | MAP@10: 0.801 -> 0.808 | Helped |
| increase number of training tuples beyond 100 (ablation) | D2AGE · six relations | NDCG/MAP | No clear effect |
Closest papers by meaning
- Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding (AAAI 2017 · similarity 0.92)
- Scalable Graph Embedding for Asymmetric Proximity (AAAI 2017 · similarity 0.88)
- UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring (NeurIPS 2025 · similarity 0.86)
- DUPLEX: Dual GAT for Complex Embedding of Directed Graphs (ICML 2024 · similarity 0.85)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.84)
- Revisiting Link Prediction: a data perspective (ICLR 2024 · similarity 0.84)
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.