Research map / Graph learning / Graph algorithms and clustering
Bernoulli Embeddings for Graphs
Vinith Misra, Sumit Bhatia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| learn Bernoulli binary embeddings instead of quantizing real-valued embeddings | node retrieval · KG, Wordnet, Slashdot, Flickr, and BlogCatalog (25-bit ranking) | test set MAP: KG: .0047 -> .0112; Wordnet: .0212 -> .1013; Slashdot: .0216 -> .0298; Flickr: .0054 -> .0161; BlogCatalog: .0094 -> .01 | Improved |
| rerank Bernoulli-retrieved nodes using observable features | Bernoulli embeddings · KG, Wordnet, Slashdot, Flickr, and BlogCatalog | test set MAP: KG: .0112 -> .0267; Wordnet: .1013 -> .0514; Slashdot: .0298 -> .0516; Flickr: .0161 -> .0487; BlogCatalog: .0181 -> .02 | Mixed |
| use uniform negative sampling rather than alternative noise distributions or curricula | Bernoulli embeddings · five graph datasets | test set MAP | No clear effect |
| use a more complex distance transformation instead of the simple linear scaling | Bernoulli embedding objective · graph link prediction | test set precision-recall | No clear effect |
Closest papers by meaning
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.89)
- GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding (ICLR 2020 · similarity 0.88)
- A Provable Framework of Learning Graph Embeddings via Summarization (AAAI 2023 · similarity 0.87)
- Wasserstein Embedding for Graph Learning (ICLR 2021 · similarity 0.86)
- Exchangeability of GNN Representations with Applications to Graph Retrieval (ICLR 2026 · similarity 0.86)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · 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.
