Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data,
but their effectiveness is often constrained by two critical challenges: oversquashing, where …

Positional and structural encodings (PSE) enable better identifiability of nodes within a
graph, rendering them essential tools for empowering modern GNNs, and in particular graph …

The Weisfeiler-Leman algorithm ($1 $-WL) is a well-studied heuristic for the graph
isomorphism problem. Recently, the algorithm has played a prominent role in understanding …

Abstract Graph Neural Networks (GNNs) have emerged as powerful tools for molecular
graph analysis. Subgraph-based GNNs focus on learning high-level local patterns beyond …

Message passing plays a vital role in graph neural networks (GNNs) for effective feature
learning. However, the over-reliance on input topology diminishes the efficacy of message …

The impact of meteorological observations on weather forecasting varies with the sensor
type, location, time, and other environmental factors. Thus, the quantitative analysis of …

In graph learning the graph and the node features both contain noisy information about the
node labels. In this paper we propose joint denoising and rewiring (JDR)--an algorithm to …

Abstract Graph Neural Networks (GNNs) have become fundamental in graph-structured
deep learning. Key paradigms of modern GNNs include message passing, graph rewiring …

Effective traffic prediction is a cornerstone of intelligent transportation systems, enabling
precise forecasts of traffic flow, speed, and congestion. While traditional spatio-temporal …

The expressive power of message-passing graph neural networks (MPNNs) is reasonably
well understood, primarily through combinatorial techniques from graph isomorphism …