DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks

TL;DR

DeHIN introduces a decentralized, hypergraph-based framework that enables scalable and efficient embedding of large-scale heterogeneous information networks by partitioning and parallel processing, with a novel alignment scheme for unified embeddings.

Contribution

The paper proposes a novel decentralized framework using hypergraph partitioning and a tree-like pipeline for scalable HIN embedding, addressing limitations of centralized methods.

Findings

Achieves efficient embedding of billion-scale HINs.

Maintains embedding quality comparable to centralized methods.

Enables effective downstream tasks like link prediction and node classification.

Abstract

Modeling heterogeneity by extraction and exploitation of high-order information from heterogeneous information networks (HINs) has been attracting immense research attention in recent times. Such heterogeneous network embedding (HNE) methods effectively harness the heterogeneity of small-scale HINs. However, in the real world, the size of HINs grow exponentially with the continuous introduction of new nodes and different types of links, making it a billion-scale network. Learning node embeddings on such HINs creates a performance bottleneck for existing HNE methods that are commonly centralized, i.e., complete data and the model are both on a single machine. To address large-scale HNE tasks with strong efficiency and effectiveness guarantee, we present \textit{Decentralized Embedding Framework for Heterogeneous Information Network} (DeHIN) in this paper. In DeHIN, we generate a distributed parallel pipeline that utilizes hypergraphs in order to infuse parallelization into the HNE task. DeHIN presents a context preserving partition mechanism that innovatively formulates a large HIN as a hypergraph, whose hyperedges connect semantically similar nodes. Our framework then adopts a decentralized strategy to efficiently partition HINs by adopting a tree-like pipeline. Then, each resulting subnetwork is assigned to a distributed worker, which employs the deep information maximization theorem to locally learn node embeddings from the partition it receives. We further devise a novel embedding alignment scheme to precisely project independently learned node embeddings from all subnetworks onto a common vector space, thus allowing for downstream tasks like link prediction and node classification.