Model Compression

An Overview of Uncertainty Calibration for Text Classification and the Role of Distillation ACL 2021 Anytime Inference with Distilled Hierarchical Neural Ensembles AAAI 2021 A Probabilistic Approach to Neural Network Pruning ICML 2021 ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective EMNLP 2021 AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks AAAI 2021 Automated Log-Scale Quantization for Low-Cost Deep Neural Networks CVPR 2021 Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021 AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression IJCAI 2021 BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021 BCNet: Searching for Network Width With Bilaterally Coupled Network CVPR 2021 Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference EMNLP 2021 Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression EMNLP 2021 Bias Loss for Mobile Neural Networks ICCV 2021 Binary Graph Neural Networks CVPR 2021 Bit-Mixer: Mixed-Precision Networks With Runtime Bit-Width Selection ICCV 2021 Block Pruning For Faster Transformers EMNLP 2021 Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring EMNLP 2021 Boost Neural Networks by Checkpoints NeurIPS 2021 CARTL: Cooperative Adversarially-Robust Transfer Learning ICML 2021 Channel Permutations for N:M Sparsity NeurIPS 2021 CHIP: CHannel Independence-based Pruning for Compact Neural Networks NeurIPS 2021 Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications EMNLP 2021 ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic CVPR 2021 Coded-InvNet for Resilient Prediction Serving Systems ICML 2021 Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation IJCAI 2021