Goto

Collaborating Authors

Engineering Agreement: The Naming Game with Asymmetric and Heterogeneous Agents

AAAI Conferences

Being popular in language evolution, cognitive science, and culture dynamics, the Naming Game has been widely used to analyze how agents reach global consensus via communications in multi-agent systems. Most prior work considered networks that are symmetric and homogeneous (e.g., vertex transitive). In this paper we consider asymmetric or heterogeneous settings that complement the current literature: 1) we show that increasing asymmetry in network topology can improve convergence rates. The star graph empirically converges faster than all previously studied graphs; 2) we consider graph topologies that are particularly challenging for naming game such as disjoint cliques or multi-level trees and ask how much extra homogeneity (random edges) is required to allow convergence or fast convergence. We provided theoretical analysis which was confirmed by simulations; 3) we analyze how consensus can be manipulated when stubborn nodes are introduced at different points of the process. Early introduction of stubborn nodes can easily influence the outcome in certain family of networks while late introduction of stubborn nodes has much less power.


Blue Brain Team Discovers a Multi-Dimensional Universe in Brain Networks

#artificialintelligence

Using mathematics in a novel way in neuroscience, the Blue Brain Project shows that the brain operates on many dimensions, not just the three dimensions that we are accustomed to. For most people, it is a stretch of the imagination to understand the world in four dimensions but a new study has discovered structures in the brain with up to eleven dimensions – ground-breaking work that is beginning to reveal the brain's deepest architectural secrets. Using algebraic topology in a way that it has never been used before in neuroscience, a team from the Blue Brain Project has uncovered a universe of multi-dimensional geometrical structures and spaces within the networks of the brain. The research, published today in Frontiers in Computational Neuroscience, shows that these structures arise when a group of neurons forms a clique: each neuron connects to every other neuron in the group in a very specific way that generates a precise geometric object. The more neurons there are in a clique, the higher the dimension of the geometric object.


Asynchronous Multi-Robot Patrolling against Intrusions in Arbitrary Topologies

AAAI Conferences

Use of game theoretical models to derive randomized mobile robot patrolling strategies has recently received a growing attention. We focus on the problem of patrolling environments with arbitrary topologies using multiple robots. We address two important issues cur rently open in the literature. We determine the smallest number of robots needed to patrol a given environment and we compute the optimal patrolling strategies along several coordination dimensions. Finally, we experimentally evaluate the proposed techniques.


Clique pooling for graph classification

arXiv.org Machine Learning

We propose a novel graph pooling operation using cliques as the unit pool. As this approach is purely topological, rather than featural, it is more readily interpretable, a better analogue to image coarsening than filtering or pruning techniques, and entirely nonparametric. The operation is implemented within graph convolution network (GCN) and GraphSAGE architectures and tested against standard graph classification benchmarks. In addition, we explore the backwards compatibility of the pooling to regular graphs, demonstrating competitive performance when replacing two-by-two pooling in standard convolutional neural networks (CNNs) with our mechanism.


Learning Chordal Markov Networks by Constraint Satisfaction

Neural Information Processing Systems

We investigate the problem of learning the structure of a Markov network from data. It is shown that the structure of such networks can be described in terms of constraints which enables the use of existing solver technology with optimization capabilities to compute optimal networks starting from initial scores computed from the data. To achieve efficient encodings, we develop a novel characterization of Markov network structure using a balancing condition on the separators between cliques forming the network. The resulting translations into propositional satisfiability and its extensions such as maximum satisfiability, satisfiability modulo theories, and answer set programming, enable us to prove the optimality of networks which have been previously found by stochastic search.