activity
20242026
collaborators

5 papers

cs.LG2026

Scale-aware Message Passing For Graph Node Classification

Qin Jiang, Chengjia Wang, Michael Lones +2

Most Graph Neural Networks (GNNs) operate at the first-order scale, even though multi-scale representations are known to be crucial in domains such as image classification. In this…

cs.LG2026

Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification

Qin Jiang, Chengjia Wang, Michael Lones +2

Spectral Graph Neural Networks (Spectral GNNs) for node classification promise frequency-domain filtering on graphs, yet rest on flawed foundations. Recent work shows that graph La…

cs.LG2025

A Comparative Analysis of Transformer Models in Social Bot Detection

Rohan Veit, Michael Lones

Social media has become a key medium of communication in today's society. This realisation has led to many parties employing artificial users (or bots) to mislead others into belie…

cs.LG2025

Demystifying MPNNs: Message Passing as Merely Efficient Matrix Multiplication

Qin Jiang, Chengjia Wang, Michael Lones +1

While Graph Neural Networks (GNNs) have achieved remarkable success, their design largely relies on empirical intuition rather than theoretical understanding. In this paper, we pre…

cs.LG2024

ScaleNet: Scale Invariance Learning in Directed Graphs

Qin Jiang, Chengjia Wang, Michael Lones +2

Graph Neural Networks (GNNs) have advanced relational data analysis but lack invariance learning techniques common in image classification. In node classification with GNNs, it is…