Research map / Probabilistic and scientific modeling / Molecules and proteins
Nonparametric Embeddings of Sparse High-Order Interaction Events
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 sparse hypergraph prior (NESH) over matrix GP without it (MGP-EF) (ablation) | NESH · Taobao, Crash, Retail | test log-likelihood | Helped |
| Use stick-breaking/log-sociability embeddings with batch normalization | NESH · Taobao, Crash, Retail | learning stability | No clear effect |
| Replace Poisson tensor factorization (CP-PTF) with nonparametric matrix GP modeling of rates (MGP-EF) | Poisson factorization baseline · Taobao, Crash, Retail | test log-likelihood | Helped |
| Use nonparametric MGP rate modeling instead of parametric CP-NPTF rate | MGP-EF · Taobao, Crash, Retail | test log-likelihood | Helped |
| Use Hawkes process local/triggering dynamics (HP-Local, HP-TF) instead of MGP-EF | MGP-EF · Taobao, Crash, Retail | test log-likelihood | Mixed |
| Use GP-PTF / HP-Local / HP-TF with no batch normalization | GP-PTF, HP-Local, HP-TF · Retail | stability across splits | Hurt |
| Sparsity ratio bounds derived for sparse hypergraph process | sparse hypergraph process (K=3) · simulated hypergraphs, alpha in [2,20] | sparsity ratio N/prod D_k | No clear effect |
Closest papers by meaning
- Nonparametric Decomposition of Sparse Tensors (ICML 2021 · similarity 0.87)
- Self-Modulating Nonparametric Event-Tensor Factorization (ICML 2020 · similarity 0.87)
- Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes (ICML 2022 · similarity 0.87)
- Statistically Robust Sparse High-order Interaction Model (AAAI 2026 · similarity 0.86)
- Hypergraph Representation Learning with Hyperlink Random Effects (NeurIPS 2026 · similarity 0.85)
- SPARTAN: A Sparse Transformer World Model Attending to What Matters (NeurIPS 2025 · 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.