Abstract: Symmetric non-negative matrix factorization (Sym-NMF) decomposes a high-dimensional symmetric non-negative matrix into a low-dimensional non-negative matrix and has been successfully used in ...

Since such semantically similar samples are ubiquitous in the graph, the problem of false negative samples is very significant. To address this issue, the paper proposes a novel model, False negative ...

Hard negative mining has shown effective in enhancing self-supervised contrastive learning (CL) on diverse data types, including graph CL (GCL). The existing hardness-aware CL methods typically treat ...

In this paper, we propose a novel integrated framework for cancer clustering known as the non-negative symmetric low-rank representation with graph regularization based on score function (NSLRG-S).

Code implements the near-linear time algorithm of Aaron Bernstein, Danupon Nanongkai, Christian Wulff-Nilsen that computes the shortest paths from a single source vertex to all other vertices in a ...

A novel method of structuring the largest and most complex datasets—from social networks to global financial markets—has won a Best Paper award at the world ... Performance tests of the algorithm ...

Quadratic graph lines are U- or Ո-shaped, which is called a parabola. A linear graph can be drawn ... For \(y = -x²\), work out \(-x²\) (which is the negative value of \(x²\)).