Spectral Bootstrapping: A self-supervised approach that eliminates the need for negative sampling, reducing computational complexity from O(N²) to O(N). Laplacian-based Augmentations: A principled ...

DRAGAN STEVANOVIĆ, WALK COUNTS AND THE SPECTRAL RADIUS OF GRAPHS, Bulletin (Académie serbe des sciences et des arts. Classe des sciences mathématiques et naturelles. Sciences mathématiques), No. 40 ...

We introduce LapDDPM, a novel conditional Graph Diffusion Probabilistic Model for robust and high-fidelity scRNA-seq generation. LapDDPM uniquely integrates graph-based representations with a ...

This paper proposes a parameter collaborative optimization algorithm for large language models, enhanced with graph spectral analysis. The goal is to improve both fine-tuning efficiency and structural ...

To address this issue, we propose an efficient and lightweight spectral-spatial feature graph contrastive learning (S2GCL) framework for robust HSI clustering. Specifically, we have designed a novel ...

We discuss the latest developments on linear system solvers for very large sparse Symmetric Diagonally Dominate system (SDD). This seemingly restrictive class of systems has received substantial ...

Abstract In this paper, we investigate some properties of the Perron vector of connected graphs. These results are used to characterize all extremal connected graphs which attain the minimum value ...