Pith. sign in

REVIEW 4 cited by

Reinitializing weights vs units for maintaining plasticity in neural networks

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

arxiv 2508.00212 v2 pith:DGEN2ZZV submitted 2025-07-31 cs.NE cs.AI

Reinitializing weights vs units for maintaining plasticity in neural networks

classification cs.NE cs.AI
keywords reinitializingnetworkunitsplasticityweightswheneffectivemaintaining
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Loss of plasticity is a phenomenon in which a neural network loses its ability to learn when trained for an extended time on non-stationary data. It is a crucial problem to overcome when designing systems that learn continually. An effective technique for preventing loss of plasticity is reinitializing parts of the network. In this paper, we compare two different reinitialization schemes: reinitializing units vs reinitializing weights. We propose a new algorithm, which we name \textit{selective weight reinitialization}, for reinitializing the least useful weights in a network. We compare our algorithm to continual backpropagation and ReDo, two previously proposed algorithms that reinitialize units in the network. Through our experiments in continual supervised learning problems, we identify two settings when reinitializing weights is more effective at maintaining plasticity than reinitializing units: (1) when the network has a small number of units and (2) when the network includes layer normalization. Conversely, reinitializing weights and units are equally effective at maintaining plasticity when the network is of sufficient size and does not include layer normalization. We found that reinitializing weights maintains plasticity in a wider variety of settings than reinitializing units.

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. Learning to Forget: Continual Learning with Adaptive Weight Decay

    cs.LG 2026-04 unverdicted novelty 6.0

    FADE adapts per-parameter weight decay rates online via approximate meta-gradient descent to improve controlled forgetting over fixed decay in online tracking and streaming classification.

  2. Calibrated Partial Resets: Preventing Policy Collapse in Continual Reinforcement Learning

    cs.LG 2026-07 conditional novelty 5.5

    Utility-scaled partial neuron resets prevent policy collapse in long-horizon continual RL while matching or beating binary-reset and uniform-decay baselines on several benchmarks.

  3. Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks

    cs.LG 2026-05 unverdicted novelty 5.0

    GXD estimates the first-order functional cost of replacing a neuron via gradient attribution to make adaptive resets more reliable for preserving plasticity in continual learning.

  4. Agentic Safety is an Epistemic Property, Not a Behavioral One

    cs.CY 2026-06 unverdicted novelty 4.0

    The paper reframes agentic safety as an epistemic property defined by teachability—the capacity to preserve future corrective leverage—rather than a behavioral property of the current policy.