Personalized PageRank (PPR) is a traditional measure for node proximity on large graphs.
For a pair of nodes and, the PPR value equals the probability that an-discounted random …

Personalized PageRank Vectors are widely used as fundamental graph-learning tools for
detecting anomalous spammers, learning graph embeddings, and training graph neural …

This paper studies the online node classification problem under a transductive learning
setting. Current methods either invert a graph kernel matrix with $\mathcal {O}(n^ 3) …

It has recently been shown that ISTA, an unaccelerated optimization method, presents
sparse updates for the $\ell_1 $-regularized undirected personalized PageRank problem …

Efficient computation of graph diffusion equations (GDEs), such as Personalized PageRank,
Katz centrality, and the Heat kernel, is crucial for clustering, training neural networks, and …

We performed a citation analysis on the Web of Science publications consisting of more than
63 million articles and over a billion citations on 254 subjects from 1981 to 2020. We …

Real-world graphs grow rapidly with edge and vertex insertions over time, motivating the
problem of efficiently maintaining robust node representation over evolving graphs. Recent …

In this paper, we introduce faster first-order primal-dual algorithms for minimizing a convex
function subject to strongly convex function constraints. Before our work, the best complexity …

With the recent advance of representation learning algorithms on graphs (eg,
DeepWalk/GraphSage) and natural languages (eg, Word2Vec/BERT), the state-of-the art …