Model Compression

Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help? ICCV 2019 Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks NeurIPS 2019 RTM Stacking Results for Machine Translation Performance Prediction ACL 2019 Same, Same But Different: Recovering Neural Network Quantization Error Through Weight Factorization ICML 2019 SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models NeurIPS 2019 SDC-causing Error Detection Based on Lightweight Vulnerability Prediction ACML 2019 SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization CVPR 2019 Sensitive-Sample Fingerprinting of Deep Neural Networks CVPR 2019 ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning Interspeech 2019 Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation CVPR 2019 Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware ICLR 2019 Small and Practical BERT Models for Sequence Labeling EMNLP 2019 SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY ICLR 2019 Structured Pruning of Neural Networks With Budget-Aware Regularization CVPR 2019 Towards Optimal Structured CNN Pruning via Generative Adversarial Learning CVPR 2019 Training a Spiking Neural Network with Equilibrium Propagation AISTATS 2019 Ultra-Compact NLU: Neuronal Network Binarization as Regularization Interspeech 2019 Universally Slimmable Networks and Improved Training Techniques ICCV 2019 Variational Bayesian Dropout With a Hierarchical Prior CVPR 2019 Variational Convolutional Neural Network Pruning CVPR 2019 Accelerating Neural Transformer via an Average Attention Network ACL 2018 Adaptive Quantization of Neural Networks ICLR 2018 Alternating Multi-bit Quantization for Recurrent Neural Networks ICLR 2018 Analyzing Knowledge Distillation in Neural Machine Translation EMNLP 2018 Approximation Algorithms for Cascading Prediction Models ICML 2018