Search Results for author:
Found 66 papers, 38 papers with code
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
In this paper, we provide a systematic study of the theoretical expressive power of order-$k$ graph transformers and sparse variants.
Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
Multi-fidelity surrogate modeling aims to learn an accurate surrogate at the highest fidelity level by combining data from multiple sources.
MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization
RL-based techniques can be used to search for prompts that when fed into a target language model maximize a set of user-specified reward functions.
MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling
Current generative models for drug discovery primarily use molecular docking to evaluate the quality of generated compounds.
Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes
In particular, we are interested in discovering instance-level causal structures in an unsupervised manner.
Target-Free Compound Activity Prediction via Few-Shot Learning
Predicting the activities of compounds against protein-based or phenotypic assays using only a few known compounds and their activities is a common task in target-free drug discovery.
Discovering Mixtures of Structural Causal Models from Time Series Data
In this work, we relax this assumption and perform causal discovery from time series data originating from a mixture of causal models.
Latent Space Symmetry Discovery
It learns a mapping from the data space to a latent space where the symmetries become linear and simultaneously discovers symmetries in the latent space.
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
The dataset is global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators.
DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting
While diffusion models can successfully generate data and make predictions, they are predominantly designed for static images.
Improving Convergence and Generalization Using Parameter Symmetries
Finally, we show that integrating teleportation into a wide range of optimization algorithms and optimization-based meta-learning improves convergence.
Disentangled Multi-Fidelity Deep Bayesian Active Learning
To balance quality and cost, various domain areas of science and engineering run simulations at multiple levels of sophistication.
Long-term Forecasting with TiDE: Time-series Dense Encoder
Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting.
Ranked #3 on
Time Series Forecasting
on ETTh2 (192) Multivariate
Understanding why shooters shoot -- An AI-powered engine for basketball performance profiling
It is crucial that the performance profiles can reflect the diverse playstyles, as well as the fast-changing dynamics of the game.
Generative Adversarial Symmetry Discovery
Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori.
On the Connection Between MPNN and Graph Transformer
Graph Transformer (GT) recently has emerged as a new paradigm of graph learning algorithms, outperforming the previously popular Message Passing Neural Network (MPNN) on multiple benchmarks.
Ranked #8 on
Node Classification
on PascalVOC-SP
Copula Conformal Prediction for Multi-step Time Series Forecasting
Accurate uncertainty measurement is a key step to building robust and reliable machine learning systems.
Symmetries, flat minima, and the conserved quantities of gradient flow
Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys.
Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts
Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs).
Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network
For that, we use more than 100, 000 research papers and build up a knowledge network with more than 64, 000 concept nodes.
Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting
In this work, we derive the generalization bounds for data augmentation and equivariant networks, characterizing their effect on learning in a unified framework.
LIMO: Latent Inceptionism for Targeted Molecule Generation
We corroborate these docking-based results with more accurate molecular dynamics-based calculations of absolute binding free energy and show that one of our generated drug-like compounds has a predicted $K_D$ (a measure of binding affinity) of $6 \cdot 10^{-14}$ M against the human estrogen receptor, well beyond the affinities of typical early-stage drug candidates and most FDA-approved drugs to their respective targets.
Multi-fidelity Hierarchical Neural Processes
MF-HNP is flexible enough to handle non-nested high dimensional data at different fidelity levels with varying input and output dimensions.
Faster Optimization on Sparse Graphs via Neural Reparametrization
In mathematical optimization, second-order Newton's methods generally converge faster than first-order methods, but they require the inverse of the Hessian, hence are computationally expensive.
Symmetry Teleportation for Accelerated Optimization
Experimentally, we show that teleportation improves the convergence speed of gradient descent and AdaGrad for several optimization problems including test functions, multi-layer regressions, and MNIST classification.
Probabilistic Symmetry for Multi-Agent Dynamics
We propose a novel deep dynamics model, Probabilistic Equivariant Continuous COnvolution (PECCO) for probabilistic prediction of multi-agent trajectories.
SELFIES and the future of molecular string representations
We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.
Taming the Long Tail of Deep Probabilistic Forecasting
We present two moment-based tailedness measurement concepts to improve performance on the difficult tail examples: Pareto Loss and Kurtosis Loss.
Approximately Equivariant Networks for Imperfectly Symmetric Dynamics
Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling.
AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands
Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery.
Neural Point Process for Learning Spatiotemporal Event Dynamics
The key construction of our approach is the nonparametric space-time intensity function, governed by a latent process.
Accelerating Optimization using Neural Reparametrization
We tackle the problem of accelerating certain optimization problems related to steady states in ODE and energy minimization problems common in physics.
Automatic Symmetry Discovery with Lie Algebra Convolutional Network
Existing equivariant neural networks require prior knowledge of the symmetry group and discretization for continuous groups.
Physics-Guided Deep Learning for Dynamical Systems: A Survey
Modeling complex physical dynamics is a fundamental task in science and engineering.
Deep Bayesian Active Learning for Accelerating Stochastic Simulation
We propose Interactive Neural Process (INP), a deep Bayesian active learning framework for learning deep surrogate models to accelerate stochastic simulations.
Quantifying Uncertainty in Deep Spatiotemporal Forecasting
Deep learning is gaining increasing popularity for spatiotemporal forecasting.
Traffic Forecasting using Vehicle-to-Vehicle Communication
In order to best utilize real-world V2V communication data, we integrate first principle models with deep learning.
Generator Surgery for Compressed Sensing
We introduce a method for achieving low representation error using generators as signal priors.
Meta-Learning Dynamics Forecasting Using Task Inference
DyAd has two parts: an encoder which infers the time-invariant hidden features of the task with weak supervision, and a forecaster which learns the shared dynamics of the entire domain.
DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
We introduce DeepGLEAM, a hybrid model for COVID-19 forecasting.
Neural Point Process for Forecasting Spatiotemporal Events
To the best of our knowledge, this is the first neural point process model that can jointly predict both the space and time of events.
Lie Algebra Convolutional Neural Networks with Automatic Symmetry Extraction
We propose to learn the symmetries during the training of the group equivariant architectures.
Learning Disentangled Representations of Videos with Missing Data
Missing data poses significant challenges while learning representations of video sequences.
Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems
While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.
Trajectory Prediction using Equivariant Continuous Convolution
Trajectory prediction is a critical part of many AI applications, for example, the safe operation of autonomous vehicles.
Deep Imitation Learning for Bimanual Robotic Manipulation
Compared to baselines, our model generalizes better and achieves higher success rates on several simulated bimanual robotic manipulation tasks.
Dynamic Relational Inference in Multi-Agent Trajectories
Neural relational inference (NRI) is a deep generative model that can reason about relations in complex dynamics without supervision.
Learning Disentangled Representations of Video with Missing Data
Missing data poses significant challenges while learning representations of video sequences.
Finding Patient Zero: Learning Contagion Source with Graph Neural Networks
% We observe that GNNs can identify P0 close to the theoretical bound on accuracy, without explicit input of dynamics or its parameters.
Aortic Pressure Forecasting with Deep Sequence Learning
The aim of this study was to forecast the mean aortic pressure five minutes in advance, using the 25 Hz time series data of previous five minutes as input.
Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis
Efficient and interpretable spatial analysis is crucial in many fields such as geology, sports, and climate science.
Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers.
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models.
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
We find that GCNs are rather restrictive in learning graph moments.
NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems.
Ranked #1 on
Multivariate Time Series Imputation
on PEMS-SF
Neural Lander: Stable Drone Landing Control using Learned Dynamics
To the best of our knowledge, this is the first DNN-based nonlinear feedback controller with stability guarantees that can utilize arbitrarily large neural nets.
Efficient Tensor Decomposition with Boolean Factors
Tensor decomposition has been extensively used as a tool for exploratory analysis.
Multi-resolution Tensor Learning for Large-Scale Spatial Data
High-dimensional tensor models are notoriously computationally expensive to train.
Long-term Forecasting using Tensor-Train RNNs
We present Tensor-Train RNN (TT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics.
Tensor Regression Meets Gaussian Processes
Low-rank tensor regression, a new model class that learns high-order correlation from data, has recently received considerable attention.
Long-term Forecasting using Higher Order Tensor RNNs
We present Higher-Order Tensor RNN (HOT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics.
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain.
Ranked #13 on
Traffic Prediction
on PEMS-BAY
Multivariate Time Series Forecasting
Spatio-Temporal Forecasting
+2
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data
Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy parameter is sufficient to model the behavior of these sources over the entire training set.
Learning from Multiway Data: Simple and Efficient Tensor Regression
In this paper, we introduce subsampled tensor projected gradient to solve the problem.
A Survey on Social Media Anomaly Detection
In this paper, we present a survey on existing approaches to address this problem.
