AAAI 2020 accepted papers on Architectures and efficiency
120 of the 1,610 papers accepted at AAAI 2020 (7.5%) are on Architectures and efficiency, compared with 6.7% at AAAI 2019. They fall into 7 topics.
See AAAI 2020 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
RNNs and normalization · 36 papers
- Where to Go Next: Modeling Long- and Short-Term User Preferences for Point-of-Interest Recommendation (439 citations)
- Neural Machine Translation with Byte-Level Subwords (186 citations)
- Visualizing Deep Networks by Optimizing with Integrated Gradients (121 citations)
- Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks (103 citations)
- Particle Filter Recurrent Neural Networks (96 citations)
- Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation (55 citations)
- New Interpretations of Normalization Methods in Deep Learning (42 citations)
- Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces (38 citations)
- Pay Your Trip for Traffic Congestion: Dynamic Pricing in Traffic-Aware Road Networks (37 citations)
- Predicting Propositional Satisfiability via End-to-End Learning (34 citations)
- Graduate Employment Prediction with Bias (33 citations)
- Deep Reservoir Computing Meets 5G MIMO-OFDM Systems in Symbol Detection (32 citations)
and 24 more in the interactive map.
Attention and transformers · 36 papers
- Interpretable Rumor Detection in Microblogs by Attending to User Interactions (214 citations)
- CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning (212 citations)
- SG-Net: Syntax-Guided Machine Reading Comprehension (199 citations)
- TreeGen: A Tree-Based Transformer Architecture for Code Generation (186 citations)
- Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network (150 citations)
- Lexical Simplification with Pretrained Encoders (94 citations)
- Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction (87 citations)
- Keywords-Guided Abstractive Sentence Summarization (84 citations)
- Multi-Scale Self-Attention for Text Classification (76 citations)
- Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER (68 citations)
- Guiding Attention in Sequence-to-Sequence Models for Dialogue Act Prediction (57 citations)
- Multi-Channel Reverse Dictionary Model (45 citations)
and 24 more in the interactive map.
Pruning and efficient tuning · 18 papers
- AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates (211 citations)
- PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-Time Execution on Mobile Devices (202 citations)
- TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection (194 citations)
- Learning Sparse Sharing Architectures for Multiple Tasks (150 citations)
- Pruning from Scratch (144 citations)
- Towards Making the Most of BERT in Neural Machine Translation (135 citations)
- Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation (81 citations)
- Acquiring Knowledge from Pre-Trained Model to Neural Machine Translation (72 citations)
- Channel Pruning Guided by Classification Loss and Feature Importance (50 citations)
- AdaFilter: Adaptive Filter Fine-Tuning for Deep Transfer Learning (45 citations)
- Dynamic Network Pruning with Interpretable Layerwise Channel Selection (43 citations)
- Reborn Filters: Pruning Convolutional Neural Networks with Limited Data (27 citations)
and 6 more in the interactive map.
Neural architecture search · 11 papers
- Neural Architecture Search Using Deep Neural Networks and Monte Carlo Tree Search (147 citations)
- Efficient Verification of ReLU-Based Neural Networks via Dependency Analysis (125 citations)
- Efficient Neural Architecture Search via Proximal Iterations (104 citations)
- TextNAS: A Neural Architecture Search Space Tailored for Text Representation (56 citations)
- InstaNAS: Instance-Aware Neural Architecture Search (46 citations)
- Binarized Neural Architecture Search (27 citations)
- M-NAS: Meta Neural Architecture Search (27 citations)
- AutoShrink: A Topology-Aware NAS for Discovering Efficient Neural Architecture (14 citations)
- Posterior-Guided Neural Architecture Search (8 citations)
- Learning to Auto Weight: Entirely Data-Driven and Highly Efficient Weighting Framework (7 citations)
- Neural Inheritance Relation Guided One-Shot Layer Assignment Search (7 citations)
CNN design · 10 papers
- ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network (188 citations)
- Gated Convolutional Networks with Hybrid Connectivity for Image Classification (68 citations)
- High Performance Depthwise and Pointwise Convolutions on Mobile Devices (61 citations)
- Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference (52 citations)
- Deep Residual-Dense Lattice Network for Speech Enhancement (43 citations)
- Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (42 citations)
- SubSpace Capsule Network (33 citations)
- DWM: A Decomposable Winograd Method for Convolution Acceleration (32 citations)
- Recognizing Instagram Filtered Images with Feature De-Stylization (18 citations)
- URNet: User-Resizable Residual Networks with Conditional Gating Module (8 citations)
Quantization · 7 papers
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT (493 citations)
- Sparsity-Inducing Binarized Neural Networks (58 citations)
- RTN: Reparameterized Ternary Network (31 citations)
- Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search (26 citations)
- Embedding Compression with Isotropic Iterative Quantization (9 citations)
- HLHLp: Quantized Neural Networks Training for Reaching Flat Minima in Loss Surface (5 citations)
- Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations (3 citations)
