← Keywords

model compression

3283 papers

Explore in graph

Also known as

MC

Co-occurring keywords

knowledge distillation (3680) large language model (12755) neural network (6616) efficient computing (779) neural network optimization (1293) transfer learning (5442) convolutional neural network (4216) neural network pruning (265) language model (4573) parameter efficiency (415)

Papers

Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022
Thrifty Neural Architecture Search for Medical Image Segmentation (Student Abstract) AAAI 2022
Tracking Down Misguiding Terms for Locating Bugs in Deep Learning-Based Software (Student Abstract) AAAI 2022
ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference ACL 2022
Attention Mechanism with Energy-Friendly Operations ACL 2022
Knowledge Distillation Meets Few-Shot Learning: An Approach for Few-Shot Intent Classification Within and Across Domains ACL 2022
EtinyNet: Extremely Tiny Network for TinyML AAAI 2022
Is Integer Arithmetic Enough for Deep Learning Training? NIPS 2022
Model Compression Using Optimal Transport WACV 2022
Federated Submodel Optimization for Hot and Cold Data Features NIPS 2022
Learning Best Combination for Efficient N:M Sparsity NIPS 2022
Knowledge Distillation As Efficient Pre-Training: Faster Convergence, Higher Data-Efficiency, and Better Transferability CVPR 2022
Resource-Adaptive Federated Learning with All-In-One Neural Composition NIPS 2022
Mixture-of-Experts with Expert Choice Routing NIPS 2022
Towards Disentangling Information Paths with Coded ResNeXt NIPS 2022
EcoFormer: Energy-Saving Attention with Linear Complexity NIPS 2022
Hilbert Distillation for Cross-Dimensionality Networks NIPS 2022
ShuffleMixer: An Efficient ConvNet for Image Super-Resolution NIPS 2022
HashFormers: Towards Vocabulary-independent Pre-trained Transformers EMNLP 2022
Efficient Adversarial Training with Robust Early-Bird Tickets EMNLP 2022
Unsupervised Non-transferable Text Classification EMNLP 2022
Modular and Parameter-Efficient Fine-Tuning for NLP Models EMNLP 2022
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token EMNLP 2022
From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models EMNLP 2022
Edinburgh’s Submission to the WMT 2022 Efficiency Task EMNLP 2022