IEEE

Spatio-Temporal Mixed Graph Neural Controlled Differential Equations with Adaptive Connection Sampling for Irregular Multivariate Time Series Anomaly Detection

Abstract: Multivariate time series data often demonstrate sparse and irregular characteristics in real-world signal processing applications, making anomaly detection challenging. This paper introduces ...
IEEE

Distributed Value Function Approximation for Collaborative Multiagent Reinforcement Learning

Abstract: In this article, we propose several novel distributed gradient-based temporal-difference algorithms for multiagent off-policy learning of linear approximation of the value function in Markov ...
GitHub

PhyGNNet: Solving spatiotemporal PDEs with Physics-informed Graph Neural Network

This repo is the official implementation of "PhyGNNet: Solving spatiotemporal PDEs with Physics-informed Graph Neural Network" by Longxiang Jiang, Liyuan Wang, Xinkun Chu, Yonghao Xiao, and Hao Zhang ...
GitHub

The official implementation for ICML2025 paper "Supercharging Graph Transformers with Advective Diffusion"

AdvDIFFormer is a graph Transformer model derived from the closed-form solution of advective diffusion equation models that are provably resilient to distribution shifts of graph topologies. The model ...
Hosted on MSN

Struggling with Algebra? Here are 10 hacks to understand equations better

Algebra can often feel intimidating, filled with strange symbols and abstract concepts that seem hard to grasp. But with the right strategies, anyone can unlock its logic and see how algebra connects ...
www.cs.cmu.edu

Monte Carlo Geometry Processing:

@article{Sawhney:2020:MCG, author = {Sawhney, Rohan and Crane, Keenan}, title = {Monte Carlo Geometry Processing: A Grid-Free Approach to PDE-Based Methods on ...