NeurIPS workshop on
Interpretable Inductive Biases
and Physically Structured Learning

December 12^th, 2020

Click here to access the workshop

Abstract

Over the last decade, deep networks have propelled machine learning to accomplish tasks previously considered far out of reach, human-level performance in image classification and game-playing. However, research has also shown that the deep networks are often brittle to distributional shifts in data: it has been shown that human-imperceptible changes can lead to absurd predictions. In many application areas, including physics, robotics, social sciences and life sciences, this motivates the need for robustness and interpretability, so that models can be trusted in practical applications. Interpretable and robust models can be constructed by incorporating prior knowledge within the model or learning process as an inductive bias, thereby avoiding overfitting and making the model easier to understand for scientists and non-machine-learning experts. In this workshop, we bring together researchers from different application areas to study the inductive biases that can be used to obtain interpretable models. We invite speakers from physics, robotics, and other related areas to share their ideas and success stories on inductive biases. We also invite researchers to submit extended abstracts for contributed talks and posters to initiate lively discussion on inductive biases and foster this growing community of researchers.

Confirmed Invited Speakers

Jeannette Bohg
Stanford University

Jessica Hamrick
DeepMind

Franziska Meier
Facebook

Frank Noé
FU Berlin

Maziar Raissi
University of Colorado, Boulder

Rose Yu
University of California, San Diego

Schedule

Time (UTC)	Event
14:30 - 14:35	Introduction and opening remarks
14:35 - 14:50	Contributed Talk: Thomas Pierrot - Learning Compositional Neural Programs for Continuous Control
14:50 - 15:10	Invited Talk: Jessica Hamrick - Structured Computation and Representation in Deep Reinforcement Learning
15:10 - 15:25	Contributed Talk: Manu Kalia - Deep learning of normal form autoencoders for universal, parameter-dependent dynamics
15:25 - 15:50	Invited Talk: Rose Yu - Physics-Guided AI for Learning Spatiotemporal Dynamics
15:50 - 16:05	Contributed Talk: Ferran Alet - Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
16:05 - 17:00	Poster Session: gather.town
17:00 - 17:25	Invited Talk: Frank Noé - PauliNet: Deep Neural Network Solution of the Electronic Schrödinger Equation
17:25 - 17:40	Contributed Talk: Kimberly Stachenfeld - Graph Networks with Spectral Message Passing
17:40 - 18:10	Invited Talk: Franziska Meier - Inductive Biases for Models and Learning-to-Learn
18:10 - 18:25	Contributed Talk: Rui Wang - Shapley Explanation Networks
18:25 - 18:55	Invited Talk: Jeanette Bohg - One the Role of Hierarchies for Learning Manipulation Skills
18:55 - 20:00	Panel Discussion
20:00 - 21:00	Poster Session: gather.town
21:00 - 21:15	Contributed Talk: Liwei Chen - Deep Learning Surrogates for Computational Fluid Dynamics
21:15 - 22:15	Invited Talk: Maziar Raissi
22:15 - 22:30	Closing Remarks

All times are in Coordinated Universal Time (UTC)

Accepted Papers

Authors	Title
Giorgio Giannone, Asha Anoosheh, Alessio Quaglino, Pierluca D’Oro, Marco Gallieri, Jonathan Masci	Real-time Classification from Short Event-CameraStreams using Input-filtering Neural ODEs
Benjamin K Miller, Mario Geiger, Tess Smidt, Frank Noé	Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
Dharma KC, Chicheng Zhang	Improving the trustworthiness of image classification models by utilizing bounding-box annotations
Marie Déchelle, Jeremie DONA, Kevin Plessis-Fraissard, Patrick Gallinari, Marina Levy	Bridging Dynamical Models and Deep Networks to Solve Forward and Inverse Problems
Sangwon Kim, Mira Jeong, Byoung Chul Ko	Is the Surrogate Model Interpretable?
Chacha Chen, Guanjie Zheng, Hua Wei, Zhenhui Li	Physics-informed Generative Adversarial Networks for Sequence Generation with Limited Data
Li-Wei Chen, Xiangyu Hu, Berkay Alp Cakal, Nils Thuerey	Deep Learning Surrogates for Computational Fluid Dynamics
Matthew Painter, Adam Prugel-Bennett, Jonathon Hare	On the Structure of Cyclic Linear Disentangled Representations
Rui Wang, Xiaoqian Wang, David I Inouye	Shapley Explanation Networks
Ričards Marcinkevičs, Julia Vogt	Interpretable Models for Granger Causality Using Self-explaining Neural Networks
Patrick Emami, Pan He, Anand Rangarajan, Sanjay Ranka	A Symmetric and Object-Centric World Model for Stochastic Environments
Benjamin Wild, David M Dormagen, Michael L Smith, Tim Landgraf	Individuality in the hive - Learning to embed lifetime social behavior of honey bees
Jiaxin Zhang, Congjie Wei, Chenglin Wu	Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
Grégoire Mialon, Dexiong Chen, Alexandre d’Aspremont, Julien Mairal	A Trainable Optimal Transport Embedding for Feature Aggregation
Kimberly Stachenfeld, Jonathan Godwin, Peter Battaglia	Graph Networks with Spectral Message Passing
Sanghoon Myung, Hyunjae Jang, Byungseon Choi, Jisu Ryu, Hyuk Kim, Sang Wuk Park, Changwook Jeong, Dae Sin Kim	A novel approach for semiconductor etching process with inductive biases
Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis	Physics-aware, data-driven discovery of slow and stable coarse-grained dynamics for high-dimensional multiscale systems
Anthony Bourached, Ryan-Rhys Griffiths, Robert Gray, Ashwani Jha, Parashkev Nachev	Generative Model-Enhanced Human Motion Prediction
Tatiana Lopez Guevara, Michael Burke, Kartic Subr, Nicholas K Taylor	IV-Posterior: Inverse Value Estimation forInterpretable Policy Certificates
Nitin Kamra, Yan Liu	Gradient-based Optimization for Multi-resource Spatial Coverage
Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu	Learning Dynamical Systems Requires Rethinking Generalization
Nima Dehmamy, Robin Walters, Yanchen Liu, Rose Yu	Lie Algebra Convolutional Networks with Automatic Symmetry Extraction
Robin Rombach, Patrick Esser, Bjorn Ommer	An Image is Worth 16 × 16 Tokens: Visual Priors for Efficient Image Synthesis with Transformers
Thao Nguyen, Maithra Raghu, Simon Kornblith	Uncovering How Neural Network Representations Vary with Width and Depth
Mario A Lino, Chris Cantwell, Anil Anthony Bharath, Eduardo Pignatelli, Stathi Fotiadis	Simulating Surface Wave Dynamics with Convolutional Networks
Amartya Sanyal, Puneet Dokania, Varun Kanade, Philip Torr	Choice of Representation Matters for Adversarial Robustness
Sameer Dharur, Purva Tendulkar, Dhruv Batra, Devi Parikh, Ramprasaath Ramasamy Selvaraju	SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency
Thomas Pierrot, Feryal Behbahani, Karim Beguir, Nando de Freitas	Learning Compositional Neural Programs for Continuous Control
Augustin Harter, Andrew Melnik, Gaurav Kumar, Dhruv Agarwal, Helge Ritter	Solving Physics Puzzles by Reasoning about Paths
Luz M. Blaz, Moises Arizpe	Modelling Advertising Awareness, an Interpretable and Differentiable Approach
Hannes Bergkvist, Peter Exner, Paul Davidsson	Constraining neural networks output by an interpolating loss function with region priors
Ellen Rushe, Brian Mac Namee	Deep Context-Aware Novelty Detection
Ferran Alet, Kenji Kawaguchi, Maria Bauza Villalonga, Nurullah Giray Kuru, Tomas Lozano-Perez, Leslie Kaelbling	Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
Pranay Pasula	Complex Skill Acquisition through Simple Skill Imitation Learning
Manu Kalia, Steven L. Brunton, Hil G.E. Meijer, Christoph Brune, Nathan Kutz	Deep learning of normal form autoencoders for universal, parameter-dependent dynamics