parameter efficiency

Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices NeurIPS 2021 Sparse Uncertainty Representation in Deep Learning with Inducing Weights NeurIPS 2021 Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021 Task Switching Network for Multi-Task Learning ICCV 2021 Towards Extremely Compact RNNs for Video Recognition With Fully Decomposed Hierarchical Tucker Structure CVPR 2021 Training Graph Neural Networks with 1000 Layers ICML 2021 A Dictionary Approach to Domain-Invariant Learning in Deep Networks NeurIPS 2020 Deep Residual-Dense Lattice Network for Speech Enhancement AAAI 2020 DeFINE: Deep Factorized Input Token Embeddings for Neural Sequence Modeling ICLR 2020 Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help ! EMNLP 2020 Dynamic Convolution: Attention Over Convolution Kernels CVPR 2020 Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement Interspeech 2020 Fast Image Reconstruction with an Event Camera WACV 2020 Fast Word Predictor for On-Device Application COLING 2020 Few-Shot Learning of Video Action Recognition Only Based on Video Contents WACV 2020 HABERTOR: An Efficient and Effective Deep Hatespeech Detector EMNLP 2020 Incremental Multi-Domain Learning with Network Latent Tensor Factorization AAAI 2020 Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps ICLR 2020 Layer-wise Guided Training for BERT: Learning Incrementally Refined Document Representations EMNLP 2020 Learning Feature Interactions with Lorentzian Factorization Machine AAAI 2020 Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation EMNLP 2020 Lightweight Text Classifier using Sinusoidal Positional Encoding AACL 2020 MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition Interspeech 2020 MergeNAS: Merge Operations into One for Differentiable Architecture Search IJCAI 2020 MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification EMNLP 2020