5 papers
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, Karish Grover +11
Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…
Text Has Curvature
Karish Grover, Hanqing Zeng, Yinglong Xia +2
Does text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mixed-curvature manifolds for compositional structur…
Feedback Control for Multi-Objective Graph Self-Supervision
Karish Grover, Theodore Vasiloudis, Han Xie +3
Can multi-task self-supervised learning on graphs be coordinated without the usual tug-of-war between objectives? Graph self-supervised learning (SSL) offers a growing toolbox of p…
CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
Karish Grover, Geoffrey J. Gordon, Christos Faloutsos
Does the intrinsic curvature of complex networks hold the key to unveiling graph anomalies that conventional approaches overlook? Reconstruction-based graph anomaly detection (GAD)…
Spectro-Riemannian Graph Neural Networks
Karish Grover, Haiyang Yu, Xiang Song +4
Can integrating spectral and curvature signals unlock new potential in graph representation learning? Non-Euclidean geometries, particularly Riemannian manifolds such as hyperbolic…