Model Compression

Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT EMNLP 2022 Pass off Fish Eyes for Pearls: Attacking Model Selection of Pre-trained Models ACL 2022 Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks AACL 2022 PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance ICML 2022 PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack COLING 2022 Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation CVPR 2022 Prior Gradient Mask Guided Pruning-Aware Fine-Tuning AAAI 2022 Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher COLING 2022 Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization IJCAI 2022 Pseudo-spherical Knowledge Distillation IJCAI 2022 Quantized Training of Gradient Boosting Decision Trees NeurIPS 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation NAACL 2022 Random Normalization Aggregation for Adversarial Defense NeurIPS 2022 Rare Gems: Finding Lottery Tickets at Initialization NeurIPS 2022 Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm NeurIPS 2022 RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise EMNLP 2022 Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks NeurIPS 2022 Rep-Net: Efficient On-Device Learning via Feature Reprogramming CVPR 2022 Resilient and Communication Efficient Learning for Heterogeneous Federated Systems ICML 2022 Resource-Adaptive Federated Learning with All-In-One Neural Composition NeurIPS 2022 Revisiting Locality Sensitive Hashing for Vocabulary Selection in Fast Neural Machine Translation EMNLP 2022 Revisiting Random Channel Pruning for Neural Network Compression CVPR 2022 Safe Distillation Box AAAI 2022 SDQ: Stochastic Differentiable Quantization with Mixed Precision ICML 2022