Research map / Label-efficient and robust learning / Recognition and long-tail
Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions
Weiyu Cheng, Yanyan Shen, Linpeng Huang
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 |
|---|---|---|---|
| Learn adaptive-order cross features instead of using fixed-order interactions | AFN · Criteo, Avazu, Movielens, and Frappe | AUC and Logloss | Mixed |
| Ensemble AFN predictions with DNN predictions | AFN · Criteo, Avazu, Movielens, and Frappe | AUC and Logloss | Improved |
| Increase the number of logarithmic neurons from too few to an appropriate number, then continue increasing it (ablation) | AFN · Frappe | AUC and Logloss | Mixed |
| Use fewer than 5 logarithmic neurons (ablation) | AFN · Frappe | AUC and Logloss | No clear effect |
| Add hidden layers above the adaptive-order cross features (ablation) | AFN · Frappe | AUC and Logloss | Improved |
| Set hidden-layer depth to 0, using a weighted sum over learned cross features (ablation) | AFN · Frappe | AUC and Logloss | No clear effect |
| Increase hidden-layer width, then exceed 600 (ablation) | AFN · Frappe | AUC and Logloss | Mixed |
Closest papers by meaning
- Factorization Machines with Regularization for Sparse Feature Interactions (JMLR 2021 · similarity 0.85)
- From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning (ICML 2025 · similarity 0.85)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.84)
- Learn2Mix: Training Neural Networks Using Adaptive Data Integration (NeurIPS 2025 · similarity 0.82)
- Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples (NeurIPS 2025 · similarity 0.82)
- Improving Adaptivity via Over-Parameterization in Sequence Models (NeurIPS 2024 · similarity 0.82)
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.
