Model Compression

Scalable Diverse Model Selection for Accessible Transfer Learning NeurIPS 2021 Scaling Up Exact Neural Network Compression by ReLU Stability NeurIPS 2021 Self-boosting for Feature Distillation IJCAI 2021 Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices NeurIPS 2021 Simple Augmentation Goes a Long Way: ADRL for DNN Quantization ICLR 2021 SmallER: Scaling Neural Entity Resolution for Edge Devices Interspeech 2021 Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks JMLR 2021 Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guided Compression WACV 2021 Stabilizing Equilibrium Models by Jacobian Regularization ICML 2021 Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks AAAI 2021 Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor ACL 2021 Structured sparsification with joint optimization of group convolution and channel shuffle UAI 2021 Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization ACL 2021 The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021 Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models EACL 2021 Topological Detection of Trojaned Neural Networks NeurIPS 2021 Towards Compact CNNs via Collaborative Compression CVPR 2021 Towards Zero-Shot Knowledge Distillation for Natural Language Processing EMNLP 2021 Training with Quantization Noise for Extreme Model Compression ICLR 2021 TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning AAAI 2021 TRQ: Ternary Neural Networks With Residual Quantization AAAI 2021 UMEC: Unified model and embedding compression for efficient recommendation systems ICLR 2021 Uncertainty-aware Binary Neural Networks IJCAI 2021 UniParma at SemEval-2021 Task 5: Toxic Spans Detection Using CharacterBERT and Bag-of-Words Model SemEval 2021 Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation EMNLP 2021