← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks IJCNLP 2022
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models EMNLP 2022
Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval COLING 2022
Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks COLING 2022
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack COLING 2022
LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency COLING 2022
Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm NIPS 2022
Synergy-of-Experts: Collaborate to Improve Adversarial Robustness NIPS 2022
Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation NIPS 2022
Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization CVPR 2022
Knowledge Distillation With the Reused Teacher Classifier CVPR 2022
Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation CVPR 2022
Federated Learning With Position-Aware Neurons CVPR 2022
Learning To Collaborate in Decentralized Learning of Personalized Models CVPR 2022
Rep-Net: Efficient On-Device Learning via Feature Reprogramming CVPR 2022
Token and Head Adaptive Transformers for Efficient Natural Language Processing COLING 2022
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach NIPS 2022
Weighted Mutual Learning with Diversity-Driven Model Compression NIPS 2022
Layer-Wised Model Aggregation for Personalized Federated Learning CVPR 2022
Contextual Similarity Distillation for Asymmetric Image Retrieval CVPR 2022
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning NIPS 2022
Elastic-Link for Binarized Neural Networks AAAI 2022
Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling EMNLP 2022
Accelerating Sparse Convolution with Column Vector-Wise Sparsity NIPS 2022
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction NIPS 2022