Research map / Learning theory and algorithms / Prediction and decision losses
Higher-Order Factorization Machines
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 third-order HOFM rather than second-order HOFM (ablation) | HOFM · NIPS | AUC: 0.856 -> 0.875 | Helped |
| Use third-order HOFM rather than second-order HOFM (ablation) | HOFM · Enzyme | AUC: 0.880 -> 0.888 | Helped |
| Use third-order HOFM rather than second-order HOFM (ablation) | HOFM · GD | AUC: 0.717 -> 0.717 | No clear effect |
| Use third-order HOFM rather than second-order HOFM (ablation) | HOFM · Movielens 100K | AUC: 0.778 -> 0.786 | Helped |
| Share parameters across degrees using augmented data | HOFM · NIPS | AUC: 0.875 -> 0.874 | No clear effect |
| Share parameters across degrees using augmented data | HOFM · Enzyme | AUC: 0.888 -> 0.887 | No clear effect |
| Share parameters across degrees using augmented data | HOFM · GD | AUC: 0.717 -> 0.704 | Hurt |
| Share parameters across degrees using augmented data | HOFM · Movielens 100K | AUC: 0.786 -> 0.787 | No clear effect |
| Increase HOFM order from 3 to 4 or 5 (ablation) | HOFM · NIPS, Enzyme, GD, Movielens 100K | AUC: 0.875 -> 0.874; 0.888 -> 0.887; 0.717 -> 0.717; 0.786 -> 0.786 | No clear effect |
| Increase shared-augmented HOFM order from 3 to 4 or 5 (ablation) | HOFM-shared-augmented · NIPS, Enzyme, GD, Movielens 100K | AUC: 0.874 -> 0.836; 0.887 -> 0.824; 0.704 -> 0.663; 0.787 -> 0.779 | Hurt |
| Learn shared weights directly with simplex constraints instead of augmented data | HOFM-shared · GD | AUC: 0.704 -> 0.721 | Helped |
Closest papers by meaning
- TMPNN: High-Order Polynomial Regression Based on Taylor Map Factorization (AAAI 2024 · similarity 0.82)
- Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks (NeurIPS 2024 · similarity 0.81)
- SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization (AAAI 2025 · similarity 0.81)
- Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization (ICLR 2025 · similarity 0.81)
- On the Crucial Role of Initialization for Matrix Factorization (ICLR 2025 · similarity 0.81)
- In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting (AAAI 2025 · similarity 0.81)
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.