Research map / Graph learning / Knowledge and temporal graphs
Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting
Tony Gracious, Ambedkar Dukkipati
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 |
|---|---|---|---|
| Use hyperedge scoring rather than pairwise edge scoring | DHE versus DE · Homogeneous datasets | MRR: +38.4% | Improved |
| Use hyperedge scoring rather than pairwise edge scoring | DHE versus DE · email-Enron and email-Eu | MAE | Mixed |
| Add interaction update (ablation) | HGDHE · Homogeneous datasets | MRR: +3.9% | Mixed |
| Add interaction update (ablation) | HGDHE · Homogeneous datasets | MAE: -24.7% | Improved |
| Add temporal drift (ablation) | DHE-drift versus RHE · Homogeneous datasets | MRR: +44% | Improved |
| Add temporal drift (ablation) | DHE-drift versus RHE · Homogeneous datasets | MAE: 42.03% reduction | Improved |
| Add temporal drift (ablation) | DHE versus RDHE · Homogeneous datasets | MRR: 90% | Improved |
| Add temporal drift (ablation) | DHE versus RDHE · Homogeneous datasets | MAE: 13.7% decrease | Improved |
| Add history aggregation (ablation) | HGDHE versus DHE · Homogeneous datasets | MRR: 1.7% | Mixed |
| Add history aggregation (ablation) | HGDHE versus DHE · Homogeneous datasets | MAE: 31.75% reduction | Improved |
| Model bipartite interactions as bipartite hyperedges instead of pairwise edges | BDHE versus BDE · CastGenre, CastKeyword, CastCrew | MRR: +23.6% | Improved |
| Use bipartite-specific modeling instead of homogeneous modeling | HGBDHE versus HGDHE · Bipartite datasets | MRR: +36.2% | Improved |
Closest papers by meaning
- Deep Representation Learning for Forecasting Recursive and Multi-Relational Events in Temporal Networks (AAAI 2025 · similarity 0.93)
- Neural Temporal Point Processes for Forecasting Directional Relations in Evolving Hypergraphs (AAAI 2025 · similarity 0.90)
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction (NeurIPS 2025 · similarity 0.88)
- A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation (AAAI 2025 · similarity 0.87)
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection (NeurIPS 2024 · similarity 0.87)
- Future Link Prediction Without Memory or Aggregation (NeurIPS 2025 · similarity 0.87)
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.
