Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
Comments ICML 2020 Workshop on Graph Representation Learning and Beyond (GRL+)
期刊&会议
ICML
International Conference on Machine Learning · 会议 · Machine Learning
Better Depth-Width Trade-offs for Neural Networks through the lens of Dynamical Systems
Comments Appeared in ICML 2020
Linear Mode Connectivity and the Lottery Ticket Hypothesis
Comments Published in ICML 2020. This submission subsumes arXiv:1903.01611 ("Stabilizing the Lottery Ticket Hypothesis" and "The Lottery Ticket Hypothesis at Scale")
Domain Adaptive Imitation Learning
Comments ICML 2020
Improving Optimization for Models With Continuous Symmetry Breaking
Comments In the proceedings of International Conference on Machine Learning (ICML 2018)
Journal ref Proceedings of the 35th International Conference on Machine Learning (ICML 2018), in PMLR 80:423-432
Sequential Explanations with Mental Model-Based Policies
Comments Accepted into ICML 2020 Workshop on Human Interpretability in Machine Learning (Spotlight)
TUDataset: A collection of benchmark datasets for learning with graphs
Comments ICML 2020 workshop "Graph Representation Learning and Beyond"
Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach
Comments 2 pages, 3 figures, Machine Learning for Media Discovery (ML4MD) Workshop at ICML 2020
One Size Fits All: Can We Train One Denoiser for All Noise Levels?
Comments Published in the 37th International Conference on Machine Learning (ICML) 2020
Geoopt: Riemannian Optimization in PyTorch
Comments Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 108, 2020, GRLB Workshop
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
Comments ICML 2020
Scalable Exact Inference in Multi-Output Gaussian Processes
Comments 31 pages, 12 figures, 5 tables, includes appendix; to appear in ICML 2020
Alleviating Privacy Attacks via Causal Learning
Comments Accepted at International Conference on Machine Learning, 2020
Prediction of the onset of cardiovascular diseases from electronic health records using multi-task gated recurrent units
Comments 5 pages, 2 figures, 2 tables, submitted at Healthcare Systems, Population Health, and the Role of Health-Tech - ICML 2020
Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
Comments Published at the 37th International Conference on Machine Learning (ICML 2020)
Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information
Comments ICML 2020
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models
Comments 22 pages, to appear at ICML 2020
GLAD: GLocalized Anomaly Detection via Human-in-the-Loop Learning
Comments Presented at the ICML-2020 Workshop on Human in the Loop Learning; 8 pages, 8 figures
Active World Model Learning with Progress Curiosity
Comments ICML 2020. Video of results at https://bit.ly/31vg7v1
Deep Representation Learning and Clustering of Traffic Scenarios
Comments Workshop on AI for Autonomous Driving, International Conference on Machine Learning (ICML) 2020
Are Hyperbolic Representations in Graphs Created Equal?
Comments Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 108, 2020, GRLB Workshop
Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
Comments Published at Workshop on AI for Autonomous Driving (AIAD), the 37th International Conference on Machine Learning, Vienna, Austria, 2020
Visualizing Transfer Learning
Comments 2020 ICML Workshop on Human Interpretability in Machine Learning (WHI 2020)
Experimental Design for Bathymetry Editing
Comments Published as a workshop paper at ICML 2020 Workshop on Real World Experiment Design and Active Learning
Modeling Coherency in Generated Emails by Leveraging Deep Neural Learners
Comments Accepted for Publication at Computación y Sistemas (CyS); Poster at CiCLing 2019 and WiML@ICML 2020
Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
Comments ICML 2020. Fabian Latorre, Paul Rolland and Nadav Hallak have contributed equally
Feature Quantization Improves GAN Training
Comments The first two authors contributed equally to this manuscript. ICML 2020. Code: https://github.com/YangNaruto/FQ-GAN
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
Comments Published at the workshop on Self-supervision in Audio and Speech (SAS) at the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria
Implicit Generative Modeling for Efficient Exploration
Comments 14 pages, 9 figures, Accepted to ICML 2020
Word-level Speech Recognition with a Letter to Word Encoder
Comments ICML 2020
