← Application Areas
Machine Learning › Application Areas ›

Knowledge Distillation

2907 directly classified papers

Papers per year

Papers

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation IJCNLP 2021
Weight Distillation: Transferring the Knowledge in Neural Network Parameters IJCNLP 2021
On Learning the Geodesic Path for Incremental Learning CVPR 2021
Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation ACML 2021
BinaryBERT: Pushing the Limit of BERT Quantization IJCNLP 2021
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains IJCNLP 2021
KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference IJCNLP 2021
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks IJCNLP 2021
Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation CORL 2021
Simulating Unknown Target Models for Query-Efficient Black-Box Attacks CVPR 2021
On the distribution of penultimate activations of classification networks UAI 2021
Data-Free Model Extraction CVPR 2021
Learning Compact Metrics for MT EMNLP 2021
Revisiting Knowledge Distillation: An Inheritance and Exploration Framework CVPR 2021
3D-to-2D Distillation for Indoor Scene Parsing CVPR 2021
Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction ACL 2021
Better Neural Machine Translation by Extracting Linguistic Information from BERT EACL 2021
Finding Spoiler Bias in Tweets by Zero-shot Learning and Knowledge Distilling from Neural Text Simplification EACL 2021
PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity Recognition EMNLP 2021
Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation EMNLP 2021
Distilling Relation Embeddings from Pretrained Language Models EMNLP 2021
AdapterFusion: Non-Destructive Task Composition for Transfer Learning EACL 2021
Annealing Knowledge Distillation EACL 2021
Informative and Controllable Opinion Summarization EACL 2021
Extremely Small BERT Models from Mixed-Vocabulary Training EACL 2021