Parameter Efficient Multimodal Transformers for Video Representation Learning
Comments Accepted to ICLR 2021
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
An Overview and Case Study of the Clinical AI Model Development Life Cycle for Healthcare Systems
Comments Accepted for oral presentation at ICLR 2020, AI for Affordable Healthcare workshop
A Unifying View on Implicit Bias in Training Linear Neural Networks
Comments 38 pages, 7 figures. Revision after ICLR 2021 camera-ready version. Figure 2 newly added, theorem statements revised, including correction of Theorem 2
Adaptive Federated Optimization
Comments Published as a conference paper at ICLR 2021
Class-conditioned Domain Generalization via Wasserstein Distributional Robust Optimization
Comments presented as a RobustML workshop paper at ICLR 2021
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
Comments Our shorter versions are accepted to ICLR 2021 Workshop on Distributed and Private Machine Learning(DPML) and MLSys 2021 GNNSys Workshop on Graph Neural Networks and Systems. The full version is under review
Model Selection's Disparate Impact in Real-World Deep Learning Applications
Comments Science and Engineering of Deep Learning Workshop, ICLR 2021
On Adversarial Robustness: A Neural Architecture Search perspective
Comments Accepted at the Workshop on Adversarial Robustness in Real-World, ICCV-2021 (previous version accepted at four ICLR-21 Workshops)
Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
Comments 15 pages, 3 figures, Accepted to International Conference on Learning Representations (ICLR) 2021 See https://github.com/ldery/ATTITTUD}{https://github.com/ldery/ATTITTUD for associated code
When Optimizing $f$-divergence is Robust with Label Noise
Comments Published as a conference paper at ICLR 2021
Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences With Attention
Comments 11 pages, 8 figures, 1 table, accepted at ICLR 2021 workshop Machine learning for preventing and combating pandemics
Neural ODE Processes
Comments ICLR 2021. 9 pages, 6 figures, 7 pages of appendices
Free Lunch for Few-shot Learning: Distribution Calibration
Comments ICLR 2021
Journal ref The 9th International Conference on Learning Representations (ICLR 2021)
Parameter-Based Value Functions
Comments Published as a conference paper at ICLR 2021
Representation Learning for Remote Sensing: An Unsupervised Sensor Fusion Approach
Comments 9 pages, 5 figures. Work completed in 2019 and submitted to ICLR in 2020. Source code available at: https://github.com/descarteslabs/contrastive_sensor_fusion. Data available at: published-datasets/osm_example_dataset.zip?folder=true&organizationId=272688069953" target="_blank" rel="noopener">https://storage.cloud.google.com/public-published-datasets/osm_example_dataset.zip?folder=true&organizationId=272688069953
Rethinking Architecture Selection in Differentiable NAS
Comments Outstanding Paper Award at ICLR 2021. The code is available at https://github.com/ruocwang/darts-pt
Maxmin Q-learning: Controlling the Estimation Bias of Q-learning
Comments ICLR 2020
Bambara Language Dataset for Sentiment Analysis
Comments 2nd Workshop on Practical ML for Developing Countries: Learning Under Limited/low Resource Scenarios, International Conference on Learning Representations, 2021
Training independent subnetworks for robust prediction
Comments Updated to the ICLR camera ready version, added reference to Soflaei et al. 2020
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
Comments Accepted @ ICML 2021; Spotlight @ ICLR 2021 "Self-Supervision for Reinforcement Learning Workshop"
Sample Efficient Policy Gradient Methods with Recursive Variance Reduction
Comments 23 pages, 2 figures, 3 tables. In ICLR 2020
Towards Robustness Against Natural Language Word Substitutions
Comments Conference paper ICLR 2021
Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy
Journal ref Workshop of RobustML ICLR 2021
SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
Comments 12 pages, 5 figures, 5 tables
Journal ref International Conference On Learning Representations (ICLR) 2021
Adversarial training may be a double-edged sword
Comments Presented as a RobustML workshop paper at ICLR 2021
Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?
Comments Published at International Conference on Learning Representations, 2021: https://openreview.net/forum?id=p5uylG94S68
Nearest Neighbor Machine Translation
Comments ICLR 2021
Heterogeneous network-based drug repurposing for COVID-19
Comments 5 pages, 3 figures, ICLR 2021 MLPCP
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
Journal ref Eighth International Conference on Learning Representations (ICLR 2020)
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Comments iclr 2021
