Research map / Label-efficient and robust learning / Recognition and long-tail
Boosting Factorization Machines via Saliency-Guided Mixup
Chenwang Wu, Defu Lian, Yong Ge, Min Zhou, Enhong Chen, Dacheng Tao
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 |
|---|---|---|---|
| double raw samples by copying (CopyFM) (ablation) | FM · Pet | AUC: 0.6776 -> 0.6739 | Hurt |
| add mixup with nearest-neighbor samples (MixFM) | FM · Frappe | LogLoss: 0.2047 -> 0.1537 | Improved |
| add mixup with nearest-neighbor samples (MixFM) | FM · Pet | AUC: 0.6776 -> 0.6846 | Improved |
| add saliency-guided mixup (SMFM) instead of random-neighbor mixup | MixFM · Pet | AUC: 0.6846 -> 0.7023 | Improved |
| add saliency-guided mixup (SMFM) instead of random-neighbor mixup | MixFM · Frappe | LogLoss: 0.1537 -> 0.1668 | Hurt |
| apply saliency-guided mixup to NFM | NFM · MovieLens | AUC: 0.9403 -> 0.9529 | Improved |
| apply saliency-guided mixup to DCN | DCN · Frappe | AUC: 0.9753 -> 0.9792 | Improved |
| apply mixup to DCN | DCN · Pet | AUC: 0.7077 -> 0.7093 | No clear effect |
| use Maxup instead of saliency-guided mixup | FM · Frappe | LogLoss: 0.1668 -> 0.3374 | Hurt |
| increase number of mixed samples n' (ablation) | MixFM/MixNFM · five datasets | AUC | Mixed |
| increase candidate neighbors p beyond 8 (ablation) | SMNFM · MovieLens | AUC | Hurt |
| increase embedding size d (ablation) | MixFM/SMFM · Frappe, MovieLens vs Amazon datasets | AUC | Mixed |
Closest papers by meaning
- Interaction-Aware Factorization Machines for Recommender Systems (AAAI 2019 · similarity 0.87)
- Attention-over-Attention Field-Aware Factorization Machine (AAAI 2020 · similarity 0.85)
- Heterogeneous Recommendation via Deep Low-rank Sparse Collective Factorization (TPAMI 2019 · similarity 0.85)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.85)
- fastFM: A Library for Factorization Machines (JMLR 2016 · similarity 0.85)
- ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering (ICLR 2024 · similarity 0.83)
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.
