Research map / Learning theory and algorithms / Matrix and tensor methods
Provable Non-linear Inductive Matrix Completion
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 |
|---|---|---|---|
| replace linear embeddings (IMC) with one-layer ReLU non-linear embeddings (NIMC) | inductive matrix completion · MovieLens ml-100k | test RMSE: 1.321 -> 1.034 | Helped |
| replace linear embeddings (IMC) with one-layer ReLU non-linear embeddings (NIMC) | inductive matrix completion · MovieLens ml-1m | test RMSE: 1.320 -> 1.021 | Helped |
| purely random initialization (alpha=1) instead of initialization near ground truth (alpha=0.1) (ablation) | gradient descent on NIMC · synthetic, k=10, d=100, n=500 | recovery rate | Hurt |
| purely random initialization on small problem (k=5, d=10) (ablation) | gradient descent on NIMC · synthetic, k=5, d=10 | recovery rate | No clear effect |
| use ReLU instead of sigmoid activation (ablation) | NIMC · synthetic recovery | samples/observations needed for exact recovery | Hurt |
Closest papers by meaning
- Inductive Matrix Completion Based on Graph Neural Networks (ICLR 2020 · similarity 0.88)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.83)
- Multi-Label Ranking Loss Minimization for Matrix Completion (AAAI 2025 · similarity 0.83)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.83)
- Efficient Network Automatic Relevance Determination (ICML 2025 · similarity 0.82)
- NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval (ICLR 2025 · 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.