Research map / Probabilistic and scientific modeling / Molecules and proteins
Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment
Chenxiao Yang, Qitian Wu, Qingsong Wen, Zhiqiang Zhou, Liang Sun, Junchi Yan
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 |
|---|---|---|---|
| replace GRU4Rec with CaseQ (GRU) | GRU4Rec · Movielens gap 30 | NDCG@10: 0.371 -> 0.406 | Improved |
| replace SASRec with CaseQ (SA) | SASRec · Movielens gap 30 | NDCG@10: 0.384 -> 0.429 | Improved |
| replace SSE-PT with CaseQ (PT) | SSE-PT · Movielens gap 30 | HR@10: 0.642 -> 0.680 | Improved |
| replace GRU4Rec with CaseQ (GRU) with no time gap | GRU4Rec · Movielens gap 0 | NDCG@10: 0.436 -> 0.448 | Improved |
| replace SASRec with CaseQ (SA) | SASRec · Yelp gap 20 | NDCG@10: 0.402 -> 0.433 | Improved |
| replace SSE-PT with CaseQ (PT) | SSE-PT · Yelp gap 20 | NDCG@10: 0.405 -> 0.440 | Improved |
| replace GRU4Rec with CaseQ (GRU), performance drop as gap grows | GRU4Rec · Movielens | NDCG drop (%): 15.0 -> 9.3 | Improved |
| replace SASRec with CaseQ (SA), performance drop as gap grows | SASRec · Movielens | NDCG drop (%): 15.2 -> 7.1 | Improved |
| replace SASRec with CaseQ (SA), performance drop as gap grows | SASRec · Yelp | NDCG drop (%): 7.6 -> 4.3 | Improved |
| replace SSE-PT with CaseQ (PT), performance drop as gap grows | SSE-PT · Yelp | NDCG drop (%): 10.3 -> 4.7 | Improved |
| use ensemble (mean pooling) or DMoE with same model size instead of single model (ablation) | GRU/LSTM/Transformer · Stack Overflow, ATM | accuracy | No clear effect |
| increase maximal gap size (temporal shift) for baselines vs CaseQ | CaseQ · Stack Overflow, ATM | accuracy | Improved |
Closest papers by meaning
- Causal Representation Learning for Generalisable Recommendation (NeurIPS 2026 · similarity 0.85)
- Towards Understanding the Universality of Transformers for Next-Token Prediction (ICLR 2025 · similarity 0.84)
- Evidential Stochastic Differential Equations for Time-Aware Sequential Recommendation (NeurIPS 2024 · similarity 0.84)
- Temporal Graph Contrastive Learning for Sequential Recommendation (AAAI 2024 · similarity 0.84)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.84)
- Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model (NeurIPS 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.
