作者
Yoshua Bengio
Machine Learning
FL Games: A federated learning framework for distribution shifts
FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data
A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition
(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment
Neural Production Systems: Learning Rule-Governed Visual Dynamics
Comments NeurIPS'21
Coordination Among Neural Modules Through a Shared Global Workspace
Comments ICLR'22 accepted paper
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions
Comments 9 pages, 6 figures
Learning Neural Causal Models with Active Interventions
Chunked Autoregressive GAN for Conditional Waveform Synthesis
Comments Published as a conference paper at ICLR 2022
Continuous-Time Meta-Learning with Forward Mode Differentiation
Combining Modular Skills in Multitask Learning
Compositional Attention: Disentangling Search and Retrieval
Graph Neural Networks with Learnable Structural and Positional Representations
Comments Code at https://github.com/vijaydwivedi75/gnn-lspe
Journal ref ICLR 2022 (https://openreview.net/pdf?id=wTTjnvGphYj)
Unifying Likelihood-free Inference with Black-box Optimization and Beyond
Comments ICLR 2022 spotlight
Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization
Towards Scaling Difference Target Propagation by Learning Backprop Targets
Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models
Comments MED-NEURIPS 2021
Multi-scale Feature Learning Dynamics: Insights for Double Descent
Gradient Starvation: A Learning Proclivity in Neural Networks
Comments Proceeding of NeurIPS 2021
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
Comments Accepted at NeurIPS 2021
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
Comments NeurIPS camera-ready version
HBert + BiasCorp -- Fighting Racism on the Web
Journal ref ltedi-1. 4 (2021) 26-33
Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Dynamic Inference with Neural Interpreters
Comments NeurIPS 2021
MINE: Mutual Information Neural Estimation
Comments 19 pages, 6 figures
Journal ref ICML 2018
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Comments iclr 2021
