conftrace_
← Techniques
Deep Learning › Techniques ›

Model Architecture

4,351 papers

Papers per year

Papers

Dynamic Network Quantization for Efficient Video Inference ICCV 2021
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent ICML 2021
Locally Adaptive Label Smoothing Improves Predictive Churn ICML 2021
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks ICML 2021
GRAND: Graph Neural Diffusion ICML 2021
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training ICML 2021
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases ICML 2021
Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021
Grid-Functioned Neural Networks ICML 2021
GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings ICML 2021
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups ICML 2021
What’s in the Box? Exploring the Inner Life of Neural Networks with Robust Rules ICML 2021
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ICML 2021
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators ICML 2021
AutoAttend: Automated Attention Representation Search ICML 2021
Prior Image-Constrained Reconstruction using Style-Based Generative Models ICML 2021
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision ICML 2021
Consensus Control for Decentralized Deep Learning ICML 2021
Better Training using Weight-Constrained Stochastic Dynamics ICML 2021
BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021
Training Graph Neural Networks with 1000 Layers ICML 2021
Tractable structured natural-gradient descent using local parameterizations ICML 2021
Learning by Turning: Neural Architecture Aware Optimisation ICML 2021
Dynamic Game Theoretic Neural Optimizer ICML 2021
Selfish Sparse RNN Training ICML 2021