NSR reframes continual learning as retrieval-based subspace memory management with SVD compression and similarity retrieval from a TaskKnowledgeBank, showing that the memory mechanism itself drives performance gains over learned allocation policies on cyclic and heterogeneous benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
NSR reframes continual learning as retrieval-based subspace memory management with SVD compression and similarity retrieval from a TaskKnowledgeBank, showing that the memory mechanism itself drives performance gains over learned allocation policies on cyclic and heterogeneous benchmarks.