Papers with network pruning techniques

4 papers
More Parameters? No Thanks! (2021.findings-acl)

Copied to clipboard

Challenge: Using network pruning, we find that there are large redundancies in MNMT models.
Approach: They propose a method to prune and retrain redundant parameters of an MNMT model to improve bilingual representations while retaining multilinguality.
Outcome: The proposed method improves bilingual representations while retaining multilinguality.
Rethinking Network Pruning – under the Pre-train and Fine-tune Paradigm (2021.naacl-main)

Copied to clipboard

Challenge: Existing pruning results on benchmark transformers, such as BERT, are not as remarkable as those of convolutional neural networks.
Approach: They propose to apply a knowledge-aware pruning process to transformer-based pre-trained language models to reduce model size and model weight.
Outcome: The proposed pruning method outperforms the leading competitors with a 20-times weight/FLOPs compression and neglectable loss in prediction accuracy.
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Recent work has shown that pruning can reduce model performance, but it can also lead to degradation in safety performance.
Approach: They propose a hierarchical safety realignment approach to prune large vision-Language Models . they quantify contribution of each attention head to safety and restore neurons .
Outcome: The proposed approach achieves significant safety improvements in LVLMs pruned post pruning.
EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks (2024.lrec-main)

Copied to clipboard

Challenge: Depending on the size of transformer-based models, they can be restricted from deployment in resource-constrained environments.
Approach: They propose to combine neural architecture search and network pruning techniques to generate and train weight-sharing super-networks that contain efficient transformer-based models.
Outcome: The proposed model achieves high-performing, high-performance subnetworks on the general language understanding evaluation and the Stanford Question Answering Dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations