Model Compression

Get More at Once: Alternating Sparse Training with Gradient Correction NeurIPS 2022 GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale NeurIPS 2022 Gradient and Mangitude Based Pruning for Sparse Deep Neural Networks AAAI 2022 Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win AAAI 2022 GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering NAACL 2022 HashFormers: Towards Vocabulary-independent Pre-trained Transformers EMNLP 2022 HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks CVPR 2022 How Well Do Sparse ImageNet Models Transfer? CVPR 2022 Implicit Feature Decoupling With Depthwise Quantization CVPR 2022 Input-Specific Robustness Certification for Randomized Smoothing AAAI 2022 Instance-Aware Dynamic Neural Network Quantization CVPR 2022 Intriguing Properties of Compression on Multilingual Models EMNLP 2022 Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding EMNLP 2022 Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC CVPR 2022 Knowledge Base Index Compression via Dimensionality and Precision Reduction ACL 2022 Knowledge Distillation: Bad Models Can Be Good Role Models NeurIPS 2022 Knowledge Distillation With the Reused Teacher Classifier CVPR 2022 KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation NAACL 2022 Lan-Bridge MT’s Participation in the WMT 2022 General Translation Shared Task EMNLP 2022 LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency COLING 2022 Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training NeurIPS 2022 Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval NAACL 2022 Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation NeurIPS 2022 Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training NAACL 2022 Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models EMNLP 2022