A Graph Diffusion Scheme for Decentralized Content Search based on Personalized PageRank

TL;DR

This paper proposes a decentralized content search method using graph diffusion and personalized PageRank to improve search accuracy in P2P networks, inspired by graph signal processing and dense information retrieval.

Contribution

It introduces a novel decentralized search approach leveraging graph filters and latent node representations, bridging P2P search with advanced graph signal processing techniques.

Findings

Effective in locating nearby relevant documents

Accuracy decreases with larger document collections

Highlights need for more advanced diffusion techniques

Abstract

Decentralization is emerging as a key feature of the future Internet. However, effective algorithms for search are missing from state-of-the-art decentralized technologies, such as distributed hash tables and blockchain. This is surprising, since decentralized search has been studied extensively in earlier peer-to-peer (P2P) literature. In this work, we adopt a fresh outlook for decentralized search in P2P networks that is inspired by advancements in dense information retrieval and graph signal processing. In particular, we generate latent representations of P2P nodes based on their stored documents and diffuse them to the rest of the network with graph filters, such as personalized PageRank. We then use the diffused representations to guide search queries towards relevant content. Our preliminary approach is successful in locating relevant documents in nearby nodes but the accuracy declines sharply with the number of stored documents, highlighting the need for more sophisticated techniques.