10 papers
Communicability-Inspired Positional Encoding (CIPE)
Yipeng Zhang, Zhongtian Sun, Pietro Liò +1
Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings should ideally induce an Attenti…
Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger
Li Sun, Ming Zhang, Wenxin Jin +5
Hypergraphs are the natural description of higher-order interactions among objects, widely applied in social network analysis, cross-modal retrieval, etc. Hypergraph Neural Network…
GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning
Zhongtian Sun, Anoushka Harit, Alexandra Cristea +2
Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data but often struggle on heterophilous graphs, where connected nodes differ i…
EWC-Guided Diffusion Replay for Exemplar-Free Continual Learning in Medical Imaging
Anoushka Harit, William Prew, Zhongtian Sun +1
Medical imaging foundation models must adapt over time, yet full retraining is often blocked by privacy constraints and cost. We present a continual learning framework that avoids…
RicciFlowRec: A Geometric Root Cause Recommender Using Ricci Curvature on Financial Graphs
Zhongtian Sun, Anoushka Harit
We propose RicciFlowRec, a geometric recommendation framework that performs root cause attribution via Ricci curvature and flow on dynamic financial graphs. By modelling evolving i…
ManifoldMind: Dynamic Hyperbolic Reasoning for Trustworthy Recommendations
Anoushka Harit, Zhongtian Sun, Suncica Hadzidedic
We introduce ManifoldMind, a probabilistic geometric recommender system for exploratory reasoning over semantic hierarchies in hyperbolic space. Unlike prior methods with fixed cur…