Model Compression

Efficient Two-Stage Progressive Quantization of BERT EMNLP 2022 E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models ACL 2022 Elastic-Link for Binarized Neural Networks AAAI 2022 Enhancing Column Generation by a Machine-Learning-Based Pricing Heuristic for Graph Coloring AAAI 2022 Equal Bits: Enforcing Equally Distributed Binary Network Weights AAAI 2022 Evaluation-Oriented Knowledge Distillation for Deep Face Recognition CVPR 2022 Exposing and Exploiting Fine-Grained Block Structures for Fast and Accurate Sparse Training NeurIPS 2022 FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server IJCAI 2022 Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better AAAI 2022 Federated Learning With Position-Aware Neurons CVPR 2022 FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction NeurIPS 2022 Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022 FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning AISTATS 2022 FNet: Mixing Tokens with Fourier Transforms NAACL 2022 Forward Compatible Training for Large-Scale Embedding Retrieval Systems CVPR 2022 From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables AAAI 2022 From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models EMNLP 2022 Get More at Once: Alternating Sparse Training with Gradient Correction NeurIPS 2022 Gradient and Mangitude Based Pruning for Sparse Deep Neural Networks AAAI 2022 GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering NAACL 2022 Graph-based Model Generation for Few-Shot Relation Extraction EMNLP 2022 Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model EMNLP 2022 Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning IJCAI 2022 HW-TSC’s Submission for the WMT22 Efficiency Task EMNLP 2022 Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation EMNLP 2022