Model Compression

Control Prefixes for Parameter-Efficient Text Generation EMNLP 2022 Cosine Model Watermarking against Ensemble Distillation AAAI 2022 COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models EMNLP 2022 CrossQE: HW-TSC 2022 Submission for the Quality Estimation Shared Task EMNLP 2022 CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference NeurIPS 2022 Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models ACL 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Dataset Inference for Self-Supervised Models NeurIPS 2022 DECORE: Deep Compression With Reinforcement Learning CVPR 2022 DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding AAAI 2022 Deep Compression of Pre-trained Transformer Models NeurIPS 2022 Deeply Tensor Compressed Transformers for End-to-End Object Detection AAAI 2022 Deep Model Reassembly NeurIPS 2022 Differentially Private Model Compression NeurIPS 2022 Discovering and Overcoming Limitations of Noise-engineered Data-free Knowledge Distillation NeurIPS 2022 DiSparse: Disentangled Sparsification for Multitask Model Compression CVPR 2022 Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model ACL 2022 DKM: Differentiable k-Means Clustering Layer for Neural Network Compression ICLR 2022 DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization ACL 2022 Dreaming To Prune Image Deraining Networks CVPR 2022 DreamShard: Generalizable Embedding Table Placement for Recommender Systems NeurIPS 2022 EasySED: Trusted Sound Event Detection with Self-Distillation AAAI 2022 Effective Model Sparsification by Scheduled Grow-and-Prune Methods ICLR 2022 Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes IJCAI 2022 Efficient Knowledge Distillation from Model Checkpoints NeurIPS 2022