1 citations · 1 across the 3 of their papers we have counts for
7 papers
Graph Anomaly Detection as Finite-Horizon Control: Training-Free Scoring via Empirical Bayes
Fred Xu, Thomas Markovich, Florence Regol +1
Node-level graph anomaly detection (GAD) identifies nodes whose attributes and interactions deviate from dominant graph regularities. Existing GAD models encode normality and anoma…
Improving Function Space Flow Matching with Kernel Optimal Transport
Fred Xu, Thomas Markovich, Barbora Barancikova +1
Generative models for function-valued data, such as time series and solutions of partial differential equations, must learn distributions over infinite-dimensional spaces. Function…
A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion
Fred Xu, Thomas Markovich, Florence Regol +1
Reliable deployment of graph neural networks requires calibration, out-of-distribution (OOD) detection, and robustness to distribution shift, yet existing methods address these nee…
Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
Fred Xu, Thomas Markovich
Graph Neural Networks have achieved impressive results across diverse network modeling tasks, but accurately estimating uncertainty on graphs remains difficult, especially under di…
When to retrain a machine learning model
Regol Florence, Schwinn Leo, Sprague Kyle +2
A significant challenge in maintaining real-world machine learning models is responding to the continuous and unpredictable evolution of data. Most practitioners are faced with the…
Understanding the Design Principles of Link Prediction in Directed Settings
Jun Zhai, Muberra Ozmen, Thomas Markovich
Link prediction is a widely studied task in Graph Representation Learning (GRL) for modeling relational data. The early theories in GRL were based on the assumption of a symmetric…
Scaling Laws for Discriminative Classification in Large Language Models
Dean Wyatte, Fatemeh Tahmasbi, Ming Li +1
Modern large language models (LLMs) represent a paradigm shift in what can plausibly be expected of machine learning models. The fact that LLMs can effectively generate sensible an…