Model Compression

Efficient Learning of Multiple NLP Tasks via Collective Weight Factorization on BERT NAACL 2022 Efficient Training of Low-Curvature Neural Networks NeurIPS 2022 Efficient Two-Stage Progressive Quantization of BERT EMNLP 2022 E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models ACL 2022 Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression ICLR 2022 End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation Interspeech 2022 Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems EMNLP 2022 Equal Bits: Enforcing Equally Distributed Binary Network Weights AAAI 2022 Exploring extreme parameter compression for pre-trained language models ICLR 2022 Exposing and Exploiting Fine-Grained Block Structures for Fast and Accurate Sparse Training NeurIPS 2022 Extracted BERT Model Leaks More Information than You Think! EMNLP 2022 EZCrop: Energy-Zoned Channels for Robust Output Pruning WACV 2022 F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization ICLR 2022 Fair NLP Models with Differentially Private Text Encoders EMNLP 2022 Fast Generic Interaction Detection for Model Interpretability and Compression ICLR 2022 Fast Vocabulary Transfer for Language Model Compression EMNLP 2022 F-coref: Fast, Accurate and Easy to Use Coreference Resolution AACL 2022 FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning IJCAI 2022 FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server IJCAI 2022 FedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning ICLR 2022 Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models NeurIPS 2022 Findings of the WMT 2022 Shared Task on Efficient Translation EMNLP 2022 Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022 Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022 Fire Together Wire Together: A Dynamic Pruning Approach With Self-Supervised Mask Prediction CVPR 2022