In the Survivable Network Design Problem (SNDP) one seeks to find a minimum cost subgraph that satisfies prescribed node-connectivity requirements. We give a novel approximation r...
— Recursive Neural Networks (RNNs) and Graph Neural Networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing fram...
Vincenzo Di Massa, Gabriele Monfardini, Lorenzo Sa...
Several reinforcement-learning techniques have already been applied to the Acrobot control problem, using linear function approximators to estimate the value function. In this pape...
In this paper, we present a general data clustering algorithm which is based on the asymmetric pairwise measure of Markov random walk hitting time on directed graphs. Unlike tradi...
We present a general framework for approximating several NP-hard problems that have two underlying properties in common. First, the problems we consider can be formulated as intege...