Knowledge Distillation

Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks ICML 2020 Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion CVPR 2020 Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion NeurIPS 2020 Dual Policy Distillation IJCAI 2020 DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles NeurIPS 2020 DynaBERT: Dynamic BERT with Adaptive Width and Depth NeurIPS 2020 Edinburgh’s Submissions to the 2020 Machine Translation Efficiency Task ACL 2020 Efficient and High-Quality Neural Machine Translation with OpenNMT ACL 2020 End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020 ACL 2020 Ensemble Distillation for Robust Model Fusion in Federated Learning NeurIPS 2020 Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast—Choose Three EMNLP 2020 Ensemble Distribution Distillation ICLR 2020 Ensemble of Students Taught by Probabilistic Teachers to Improve Speech Emotion Recognition Interspeech 2020 ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks NeurIPS 2020 Explaining Knowledge Distillation by Quantifying the Knowledge CVPR 2020 Exploit and Replace: An Asymmetrical Two-Stream Architecture for Versatile Light Field Saliency Detection AAAI 2020 Exploring the Boundaries of Low-Resource BERT Distillation EMNLP 2020 Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT ACL 2020 Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation NeurIPS 2020 FastBERT: a Self-distilling BERT with Adaptive Inference Time ACL 2020 FasterSeg: Searching for Faster Real-time Semantic Segmentation ICLR 2020 FastFormers: Highly Efficient Transformer Models for Natural Language Understanding EMNLP 2020 Fast RDMA-based Ordered Key-Value Store using Remote Learned Cache OSDI 2020 Feature-map-level Online Adversarial Knowledge Distillation ICML 2020 FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction EMNLP 2020