Pith. sign in

REVIEW 9 cited by

Continual Learning via Neural Pruning

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 1903.04476 v1 pith:TSXJWOAA submitted 2019-03-11 cs.LG cs.NEq-bio.NCstat.ML

classification cs.LGcs.NEq-bio.NCstat.ML
keywords clnplearningtaskscontinualneuronsperformancecapacityforgetting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and filters of the sparsified network and cause zero deterioration to the performance of previous tasks. In order to deal with the possible compromise between model sparsity and performance, we formalize and incorporate the concept of graceful forgetting: the idea that it is preferable to suffer a small amount of forgetting in a controlled manner if it helps regain network capacity and prevents uncontrolled loss of performance during the training of future tasks. CLNP also provides simple continual learning diagnostic tools in terms of the number of free neurons left for the training of future tasks as well as the number of neurons that are being reused. In particular, we see in experiments that CLNP verifies and automatically takes advantage of the fact that the features of earlier layers are more transferable. We show empirically that CLNP leads to significantly improved results over current weight elasticity based methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Learning in Deep Networks under Dale's Constraint

    cs.AI 2026-08 reject novelty 7.0 of 10

    An on-off two-channel network with fixed-sign synapses and local Hebbian learning is claimed to recover backpropagation exactly under symmetric weights and to beat comparable vanilla networks on Tiny ImageNet.

  2. When Does Continual Learning Require Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.

  3. Learning without Isolation: Pathway Protection for Continual Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    LwI fuses old and new models with graph matching, matching similar channels in shallow layers and dissimilar channels in deep layers, to reduce catastrophic forgetting without storing old data.

  4. Continual Learning Beyond Experience Rehearsal and Full Model Surrogates

    cs.LG 2025-05 conditional novelty 5.0 of 10

    SPARC achieves strong continual learning accuracy with a fraction of the parameters of surrogate-based methods by combining task-specific depthwise filters with shared pointwise filters updated by exponential averaging.

  5. Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Eidetic Learning freezes each task's important neurons and prunes connections from recycled neurons, making catastrophic forgetting impossible for the retained subnetwork.

  6. Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning

    cs.CV 2024-12 conditional novelty 5.0 of 10

    Domain shift reduces catastrophic forgetting in class-incremental learning, and the DisCo module transfers that benefit to ordinary benchmarks by enforcing task-separated features with contrastive losses.

  7. Listen, Look, and Learn: Learning Without Forgetting through SAM-Audio

    cs.CV 2026-06 unverdicted novelty 4.0 of 10

    Integrates SAM-Audio dense representations with guided attention and dual distillation for audio-visual class-incremental learning, reporting consistent outperformance on benchmarks.

  8. Understanding and Analyzing Model Robustness and Knowledge-Transfer in Multilingual Neural Machine Translation using TX-Ray

    cs.CL 2024-12 conditional novelty 4.0 of 10

    Sequential transfer with English-English pre-training yields a small BLEU gain for English-Spanish only, and neuron pruning consistently hurts low-resource NMT.

  9. Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networks

    cs.NE 2023-09 unverdicted novelty 4.0 of 10

    SOR-SNN employs Self-Organizing Regulation networks to reorganize a single SNN into sparse pathways, achieving better performance, energy efficiency, memory use, backward transfer, and self-repair on continual learnin...

Pith tools