Strategies for Utility Maximization in Social Groups with Preferential Exploration

TL;DR

This paper develops decentralized algorithms for social group nodes to maximize utility through preferential exploration and strategic exchanges, balancing cost and cooperation.

Contribution

It introduces novel algorithms based on the Stable Roommates Problem for utility maximization in social groups with preferential exploration and exchange strategies.

Findings

Decentralized algorithms achieve near-optimal utility in large groups.

Preferential exploration improves link formation efficiency.

Behavioral regimes influence the minimal cost for utility maximization.

Abstract

We consider a \emph{Social Group} of networked nodes, seeking a "universe" of segments for maximization of their utility. Each node has a subset of the universe, and access to an expensive link for downloading data. Nodes can also acquire the universe by exchanging copies of segments among themselves, at low cost, using inter-node links. While exchanges over inter-node links ensure minimum or negligible cost, some nodes in the group try to exploit the system. We term such nodes as `non-reciprocating nodes' and prohibit such behavior by proposing the "Give-and-Take" criterion, where exchange is allowed iff each participating node has segments unavailable with the other. Following this criterion for inter-node links, each node wants to maximize its utility, which depends on the node's segment set available with the node. Link activation among nodes requires mutual consent of participating nodes. Each node tries to find a pairing partner by preferentially exploring nodes for link formation and unpaired nodes choose to download a segment using the expensive link with segment aggressive probability. We present various linear complexity decentralized algorithms based on \emph{Stable Roommates Problem} that can be used by nodes (as per their behavioral nature) for choosing the best strategy based on available information. Then, we present decentralized randomized algorithm that performs close to optimal for large number of nodes. We define \emph{Price of Choices} for benchmarking performance for social groups (consisting of non-aggressive nodes only). We evaluate performances of various algorithms and characterize the behavioral regime that will yield best results for node and social group, spending the minimal on expensive link. We consider social group consisting of non-aggressive nodes and benchmark performances of proposed algorithms with the optimal.