3.2k citations · 6.9k across the 41 of their papers we have counts for
19 papers · 1 filter
Deep Minds and Shallow Probes
Su Hyeong Lee, Risi Kondor
Neural representations are not unique objects. Even when two systems realize the same downstream computation, their hidden coordinates may differ by reparameterization. A probe fam…
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
Su Hyeong Lee, Risi Kondor, Richard Ngo
We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log…
Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size
Smayan Khanna, Doruk Efe Gökmen, Risi Kondor +1
Graph Contrastive Learning (GCL) has emerged as a leading paradigm for self-supervised learning on graphs, with strong performance reported on standardized datasets and growing app…
Learning to Solve Multiresolution Matrix Factorization by Manifold Optimization and Evolutionary Metaheuristics
Truong Son Hy, Thieu Khang, Risi Kondor
Multiresolution Matrix Factorization (MMF) is unusual amongst fast matrix factorization algorithms in that it does not make a low rank assumption. This makes MMF especially well su…
Sign Rank Limitations for Inner Product Graph Decoders
Su Hyeong Lee, Qingqi Zhang, Risi Kondor
Inner product-based decoders are among the most influential frameworks used to extract meaningful data from latent embeddings. However, such decoders have shown limitations in repr…
Transformers are efficient hierarchical chemical graph learners
Zihan Pengmei, Zimu Li, Chih-chan Tien +2
Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or e…
Modeling Polypharmacy and Predicting Drug-Drug Interactions using Deep Generative Models on Multimodal Graphs
Nhat Khang Ngo, Truong Son Hy, Risi Kondor
Latent representations of drugs and their targets produced by contemporary graph autoencoder models have proved useful in predicting many types of node-pair interactions on large n…
Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
Nhat Khang Ngo, Truong Son Hy, Risi Kondor
Contemporary graph learning algorithms are not well-defined for large molecules since they do not consider the hierarchical interactions among the atoms, which are essential to det…
Fast Temporal Wavelet Graph Neural Networks
Duc Thien Nguyen, Manh Duc Tuan Nguyen, Truong Son Hy +1
Spatio-temporal signals forecasting plays an important role in numerous domains, especially in neuroscience and transportation. The task is challenging due to the highly intricate…
Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism
Zimu Li, Zihan Pengmei, Han Zheng +3
Many learning tasks, including learning potential energy surfaces from ab initio calculations, involve global spatial symmetries and permutational symmetry between atoms or general…
Temporal Multiresolution Graph Neural Networks For Epidemic Prediction
Truong Son Hy, Viet Bach Nguyen, Long Tran-Thanh +1
In this paper, we introduce Temporal Multiresolution Graph Neural Networks (TMGNN), the first architecture that both learns to construct the multiscale and multiresolution graph st…
Symmetry Group Equivariant Architectures for Physics
Alexander Bogatskiy, Sanmay Ganguly, Thomas Kipf +8
Physical theories grounded in mathematical symmetries are an essential component of our understanding of a wide range of properties of the universe. Similarly, in the domain of mac…
Learning Multiresolution Matrix Factorization and its Wavelet Networks on Graphs
Truong Son Hy, Risi Kondor
Multiresolution Matrix Factorization (MMF) is unusual amongst fast matrix factorization algorithms in that it does not make a low rank assumption. This makes MMF especially well su…
Multiresolution Equivariant Graph Variational Autoencoder
Truong Son Hy, Risi Kondor
In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolut…
Autobahn: Automorphism-based Graph Neural Nets
Erik Henning Thiede, Wenda Zhou, Risi Kondor
We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. In an Autobahn, we decompose the graph into a collection of subgraphs and a…
ATOM3D: Tasks On Molecules in Three Dimensions
Raphael J. L. Townshend, Martin Vögele, Patricia Suriana +10
Computational methods that operate on three-dimensional molecular structure have the potential to solve important questions in biology and chemistry. In particular, deep neural net…
The general theory of permutation equivarant neural networks and higher order graph variational encoders
Erik Henning Thiede, Truong Son Hy, Risi Kondor
Previous work on symmetric group equivariant neural networks generally only considered the case where the group acts by permuting the elements of a single vector. In this paper we…
N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
Risi Kondor
We describe N-body networks, a neural network architecture for learning the behavior and properties of complex many body physical systems. Our specific application is to learn atom…
Covariant Compositional Networks For Learning Graphs
Risi Kondor, Hy Truong Son, Horace Pan +2
Most existing neural networks for learning graphs address permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors…