pith. sign in

arxiv: 2311.02428 · v1 · pith:7HUAXI2Lnew · submitted 2023-11-04 · 💻 cs.CV · cs.LG

Task Arithmetic with LoRA for Continual Learning

classification 💻 cs.CV cs.LG
keywords methodcontinuallearningmodelsproblemtasktrainingarithmetic
0
0 comments X
read the original abstract

Continual learning refers to the problem where the training data is available in sequential chunks, termed "tasks". The majority of progress in continual learning has been stunted by the problem of catastrophic forgetting, which is caused by sequential training of the model on streams of data. Moreover, it becomes computationally expensive to sequentially train large models multiple times. To mitigate both of these problems at once, we propose a novel method to continually train transformer-based vision models using low-rank adaptation and task arithmetic. Our method completely bypasses the problem of catastrophic forgetting, as well as reducing the computational requirement for training models on each task. When aided with a small memory of 10 samples per class, our method achieves performance close to full-set finetuning. We present rigorous ablations to support the prowess of our method.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams

    cs.CV 2026-05 unverdicted novelty 7.0

    Domain-incremental video learning that permits forgetting through per-domain LoRA adapters and recovers the matching adapter at inference via test-time training on a self-supervised MAE reconstruction head.

  2. Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents

    cs.AI 2026-06 unverdicted novelty 6.0

    EVAF, a surprise- and valence-gated LoRA mechanism, provides memory depth for goal persistence in language agents via the loop-drift protocol, complementary to retrieval.

  3. EVAF: A Test-Retest Protocol for Selective Parametric Consolidation

    cs.LG 2026-06 unverdicted novelty 5.0

    EVAF and test-retest protocol show selective parametric consolidation of high-valence experiences in GPT-2 and TinyLlama while preserving factual retrieval.

  4. Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

    cs.LG 2024-08 accept novelty 4.0

    The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.