Research map / Continual learning / Online and replay-based
Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes online functional tensor decomposition (OFTD), which models a spatial-temporal continuous function via CP decomposition with coordinate-based implicit neural representations, updated online for streaming tensor completion.
Problem
Processing high-velocity streaming tensor data (e.g., traffic flow, weather) with missing entries, where online tensor decomposition must adapt to new data without retraining from scratch.
Approach
Represents a spatial-temporal continuous function using a CP tensor decomposition whose factors are parameterized by coordinate-based implicit neural representations, combined with continual learning for online updates.
Experimental setup
Builds on: CP tensor decomposition coordinate-based implicit neural representation
Closest papers by meaning
- Functional Complexity-adaptive Temporal Tensor Decomposition (NeurIPS 2025 · similarity 0.88)
- Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data (ICLR 2024 · similarity 0.86)
- Coarse-To-Fine Tensor Trains for Compact Visual Representations (ICML 2024 · similarity 0.85)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.84)
- Geometry-aware training of factorized layers in tensor Tucker format (NeurIPS 2024 · similarity 0.84)
- Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods (NeurIPS 2024 · similarity 0.84)
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.