REVIEW 5 cited by
TRGP: Trust Region Gradient Projection for Continual Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
TRGP: Trust Region Gradient Projection for Continual Learning
read the original abstract
Catastrophic forgetting is one of the major challenges in continual learning. To address this issue, some existing methods put restrictive constraints on the optimization space of the new task for minimizing the interference to old tasks. However, this may lead to unsatisfactory performance for the new task, especially when the new task is strongly correlated with old tasks. To tackle this challenge, we propose Trust Region Gradient Projection (TRGP) for continual learning to facilitate the forward knowledge transfer based on an efficient characterization of task correlation. Particularly, we introduce a notion of `trust region' to select the most related old tasks for the new task in a layer-wise and single-shot manner, using the norm of gradient projection onto the subspace spanned by task inputs. Then, a scaled weight projection is proposed to cleverly reuse the frozen weights of the selected old tasks in the trust region through a layer-wise scaling matrix. By jointly optimizing the scaling matrices and the model, where the model is updated along the directions orthogonal to the subspaces of old tasks, TRGP can effectively prompt knowledge transfer without forgetting. Extensive experiments show that our approach achieves significant improvement over related state-of-the-art methods.
Forward citations
Cited by 5 Pith papers
-
A Prototypical Signature Approach for Writer-Independent Offline Signature Verification
Prototypical signatures enable generation of diverse negative samples for writer-independent offline signature verification, improving skilled forgery detection and allowing scalable linear SVM alternatives to RBF models.
-
Invariant Reasoning Directions in Latent Trajectories of Language Models
TILR identifies low-rank invariant subspaces from contrastive latent trajectory differences in LLMs and constrains interventions to them, improving paraphrase consistency by ~10% and reducing variance by up to 50%.
-
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.
-
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
-
A Faster Path to Continual Learning
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.