Research map / Architectures and efficiency / RNNs and normalization
Predicting Temporal Sets with Simplified Fully Connected Networks
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 |
|---|---|---|---|
| use SFCNTSP instead of ETGNN | temporal set prediction · JingDong, transductive, K=40 | Recall: 0.4752 -> 0.5018 | Helped |
| use SFCNTSP instead of ETGNN | temporal set prediction · DC, transductive, K=40 | Recall: 0.6580 -> 0.6755 | Helped |
| use SFCNTSP instead of ETGNN | temporal set prediction · TaoBao, transductive, K=40 | Recall: 0.4596 -> 0.4717 | Helped |
| use SFCNTSP instead of ETGNN | temporal set prediction · TMS, transductive, K=40 | Recall: 0.7271 -> 0.7415 | Helped |
| replace SFCN with a one- or two-layer FCN (ablation) | SFCNTSP · JingDong, K=40 | Recall: 0.5018 -> 0.4974; 0.5018 -> 0.4941 | Hurt |
| replace SFCN with a one- or two-layer MLP (ablation) | SFCNTSP · JingDong, K=40 | Recall: 0.5018 -> 0.4968; 0.5018 -> 0.4657 | Hurt |
| replace SFCN with a one- or two-layer MLP (ablation) | SFCNTSP · DC, K=40 | Recall: 0.6755 -> 0.6696; 0.6755 -> 0.6660 | Hurt |
| replace SFCN with a one- or two-layer MLP (ablation) | SFCNTSP · TaoBao, K=40 | Recall: 0.4717 -> 0.4682; 0.4717 -> 0.4654 | Hurt |
| replace SFCN with a one- or two-layer MLP (ablation) | SFCNTSP · TMS, K=40 | Recall: 0.7415 -> 0.7371; 0.7415 -> 0.7369 | Hurt |
| remove temporal dependencies learning (ablation) | SFCNTSP · all four benchmarks | Recall, NDCG, and PHR | Hurt |
| remove element relationships learning (ablation) | SFCNTSP · all four benchmarks | Recall, NDCG, and PHR | Hurt |
| remove channel correlations learning (ablation) | SFCNTSP · all four benchmarks | Recall, NDCG, and PHR | Hurt |
Closest papers by meaning
- Simple and Efficient Heterogeneous Temporal Graph Neural Network (NeurIPS 2025 · similarity 0.86)
- Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs (NeurIPS 2024 · similarity 0.85)
- Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks (AAAI 2025 · similarity 0.85)
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting (NeurIPS 2026 · similarity 0.85)
- State Space Models on Temporal Graphs: A First-Principles Study (NeurIPS 2024 · similarity 0.84)
- PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks (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.