← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation ACL 2021
OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization AAAI 2021
CAPE: Context-Aware Private Embeddings for Private Language Learning EMNLP 2021
Iterative Deep Model Compression and Acceleration in the Frequency Domain ACML 2021
Layer-Wise Neural Network Compression via Layer Fusion ACML 2021
Learning Diverse-Structured Networks for Adversarial Robustness ICML 2021
Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing ICML 2021
Revisiting Pretraining with Adapters IJCNLP 2021
4-Bit Quantization of LSTM-Based Speech Recognition Models INTERSPEECH 2021
Configurable Privacy-Preserving Automatic Speech Recognition INTERSPEECH 2021
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework ICML 2021
Accurate Post Training Quantization With Small Calibration Sets ICML 2021
A Unified Lottery Ticket Hypothesis for Graph Neural Networks ICML 2021
RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation EMNLP 2021
Efficient Attentions for Long Document Summarization NAACL 2021
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge NIPS 2021
S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks NIPS 2021
Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples NIPS 2021
DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks NIPS 2021
Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks NIPS 2021
ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting ICCV 2021
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift ICCV 2021
Uncertainty-aware Binary Neural Networks IJCAI 2021
Decomposable-Net: Scalable Low-Rank Compression for Neural Networks IJCAI 2021
Against Membership Inference Attack: Pruning is All You Need IJCAI 2021