Model Compression

Measuring and Reducing Model Update Regression in Structured Prediction for NLP NeurIPS 2022 Mixture-of-Experts with Expert Choice Routing NeurIPS 2022 MLink: Linking Black-Box Models for Collaborative Multi-Model Inference AAAI 2022 MockingBERT: A Method for Retroactively Adding Resilience to NLP Models COLING 2022 Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems EMNLP 2022 MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation NAACL 2022 MONICA2: Mobile Neural Voice Command Assistants towards Smaller and Smarter AAAI 2022 Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error CVPR 2022 Multi-Dimensional Dynamic Model Compression for Efficient Image Super-Resolution WACV 2022 Multilingual Code Snippets Training for Program Translation AAAI 2022 Multi-View Attention Transfer for Efficient Speech Enhancement Interspeech 2022 Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation CVPR 2022 Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise NeurIPS 2022 Online Convolutional Re-Parameterization CVPR 2022 Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning NeurIPS 2022 Optimal channel selection with discrete QCQP AISTATS 2022 Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training ICML 2022 Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling NeurIPS 2022 PAC-Net: A Model Pruning Approach to Inductive Transfer Learning ICML 2022 PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion EMNLP 2022 Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition Interspeech 2022 Parameter-Efficient Legal Domain Adaptation EMNLP 2022 Parameter-Efficient Masking Networks NeurIPS 2022 Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models COLING 2022 Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval COLING 2022