42 citations · 83 across the 15 of their papers we have counts for
15 papers
The Role of Symmetry in Optimizing Overparameterized Networks
Kusha Sareen, Mohammad Pedramfar, Sékou-Oumar Kaba +2
Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmet…
Inverting Data Transformations via Diffusion Sampling
Jinwoo Kim, Sékou-Oumar Kaba, Jiyun Park +2
We study the problem of transformation inversion on general Lie groups: a datum is transformed by an unknown group element, and the goal is to recover an inverse transformation tha…
LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui +12
Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented explorat…
Energy Loss Functions for Physical Systems
Sékou-Oumar Kaba, Kusha Sareen, Daniel Levy +1
Effectively leveraging prior knowledge of a system's physics is crucial for applications of machine learning to scientific domains. Previous approaches mostly focused on incorporat…
Accurate and scalable exchange-correlation with deep learning
Giulia Luise, Chin-Wei Huang, Thijs Vogels +25
Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable…
Improving Equivariant Networks with Probabilistic Symmetry Breaking
Hannah Lawrence, Vasco Portilheiro, Yan Zhang +1
Equivariance encodes known symmetries into neural networks, often enhancing generalization. However, equivariant networks cannot break symmetries: the output of an equivariant netw…
On the Identifiability of Causal Abstractions
Xiusi Li, Sékou-Oumar Kaba, Siamak Ravanbakhsh
Causal representation learning (CRL) enhances machine learning models' robustness and generalizability by learning structural causal models associated with data-generating processe…
Symmetry-Aware Generative Modeling through Learned Canonicalization
Kusha Sareen, Daniel Levy, Arnab Kumar Mondal +3
Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The existing generative modeling paradigm for…
Symmetry Breaking and Equivariant Neural Networks
Sékou-Oumar Kaba, Siamak Ravanbakhsh
Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design. However, the relationship between symmetry and t…
Equivariant Adaptation of Large Pretrained Models
Arnab Kumar Mondal, Siba Smarak Panigrahi, Sékou-Oumar Kaba +2
Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate a…
Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Daniel Levy, Sékou-Oumar Kaba, Carmelo Gonzales +2
We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node. We formulate the extension and show that it improves perfo…
Equivariant Networks for Crystal Structures
Sékou-Oumar Kaba, Siamak Ravanbakhsh
Supervised learning with deep models has tremendous potential for applications in materials science. Recently, graph neural networks have been used in this context, drawing direct…
Equivariance with Learned Canonicalization Functions
Sékou-Oumar Kaba, Arnab Kumar Mondal, Yan Zhang +2
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations. In this paper, we propose an alternati…
Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests
Sékou-Oumar Kaba, Benjamin Groleau-Paré, Marc-Antoine Gauthier +3
Magnetic materials are crucial components of many technologies that could drive the ecological transition, including electric motors, wind turbine generators and magnetic refrigera…
Gradient Starvation: A Learning Proclivity in Neural Networks
Mohammad Pezeshki, Sékou-Oumar Kaba, Yoshua Bengio +3
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-…