Research map / Label-efficient and robust learning / Recognition and long-tail
Little Is Much: Bridging Cross-Platform Behaviors through Overlapped Crowds
Meng Jiang, Peng Cui, Nicholas Jing Yuan, Xing Xie, Shiqiang Yang
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 |
|---|---|---|---|
| add pairwise-similarity supervision from overlapping users instead of hard-aligned latent spaces (ablation) | XPTRANS · Tweet entity -> Douban movie, non-overlapping | RMSE: 1.164 -> 0.722 | Improved |
| use pairwise-similarity constraints instead of aligned latent features (ablation) | XPTRANS · Tweet entity -> Douban movie, non-overlapping | MAP: 0.702 -> 0.820 | Improved |
| use XPTRANS vs CBT for non-overlapping users | cross-platform transfer · Tweet entity -> Douban movie | RMSE: 1.290 -> 0.722 | Improved |
| use XPTRANS vs CBT for overlapping users | cross-platform transfer · Tweet entity -> Douban movie | RMSE: 0.767 -> 0.715 | Improved |
| use XPTRANS vs CBT for non-overlapping users | cross-platform transfer · Douban book -> Weibo tag | MAP: 0.477 -> 0.533 | Improved |
| use XPTRANS vs CBT | cross-platform transfer · Douban movie newcomers | RMSE: 1.737 -> 1.569 | Improved |
| transfer auxiliary platform data (XPTRANS vs no transfer CMF) | matrix factorization · Tweet entity -> Douban movie, non-overlapping | RMSE: 1.439 -> 0.722 | Improved |
| use XPTRANS vs CBT for overlapping users | cross-platform transfer · Douban book -> Weibo tag | MAP: 0.675 -> 0.705 | Improved |
| increase fraction of overlapping users/behaviors used for training (ablation) | XPTRANS · Tweet entity -> Douban movie | RMSE and MAP: 26% active users or 60% behaviors reach overlapped-user accuracy | Improved |
Closest papers by meaning
- Link Prediction in Multilayer Networks via Cross-Network Embedding (AAAI 2024 · similarity 0.82)
- Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data (AAAI 2025 · similarity 0.82)
- Decoupling User Relationships Guides Information Diffusion Prediction (Student Abstract) (AAAI 2024 · similarity 0.81)
- Ghidorah: Towards Robust Multi-Scale Information Diffusion Prediction via Test-Time Training (AAAI 2025 · similarity 0.81)
- Learning Accurate and Bidirectional Transformation via Dynamic Embedding Transportation for Cross-Domain Recommendation (AAAI 2024 · similarity 0.80)
- Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design (ICML 2025 · similarity 0.80)
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.
