Task-Guided Pair Embedding in Heterogeneous Network

Abstract

Many real-world tasks solved by heterogeneous network embedding methods can be cast as modeling the likelihood of a pairwise relationship between two nodes. For example, the goal of author identification task is to model the likelihood of a paper being written by an author (paper-author pairwise relationship). Existing taskguided embedding methods are node-centric in that they simply measure the similarity between the node embeddings to compute the likelihood of a pairwise relationship between two nodes. However, we claim that for task-guided embeddings, it is crucial to focus on directly modeling the pairwise relationship. In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e.g., paper-author relationship in author identification). To this end, we 1) propose to learn a pair embedding under the guidance of its associated context path, i.e., a sequence of nodes between the pair, and 2) devise the pair validity classifier to distinguish whether the pair is valid with respect to the specific task at hand. By introducing pair embeddings that capture the semantics behind the pairwise relationships, we are able to learn the fine-grained pairwise relationship between two nodes, which is paramount for task-guided embedding methods. Extensive experiments on author identification task demonstrate that TaPEm outperforms the state-of-the-art methods, especially for authors with few publication records.

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

“…In a similar spirit, Chen et al proposes to learn relationspecific projection matrices [30] in the divided bipartite/homogeneous graphs in order to learn more expressive node embeddings. Among heterogeneous graph embedding methods, a large body of recent works [31]- [34] make use of the heterogeneous contexts within meta paths [9] to facilitate node representation learning for downstream tasks. Essentially, a meta path is a sequence of heterogeneous nodes linked via various types of relations [35].…”

Unsupervised Differentiable Multi-aspect Network Embedding

“…• Models a single aspect -M2V++ [5]: It learns embeddings for nodes in a HetNet by performing meta-path guided random walk followed by heterogeneous skip-gram. Following [19], we leverage the paper abstract for paper embeddings. -Camel [32]: It is a task-guided heterogeneous network embedding method developed for the author identification task in which content-aware skip-gram is introduced.…”

“…-Camel [32]: It is a task-guided heterogeneous network embedding method developed for the author identification task in which content-aware skip-gram is introduced. • Models multiple aspects -TaPEm [19]: It is the state-of-the-art task-guided heterogeneous network embedding method that introduces the pair embedding framework to directly capture the pairwise relationship between two heterogeneous nodes.…”

“…However, these methods define the aspects based on the edges whose ground-truth labels should be predefined (e.g., the edge between "Obama" and "Honolulu" is labeled as "was_born_in"), which is not always the case in reality. Finally, TaPEm [19] introduces the pair embedding framework that directly models the relationship between two nodes of different types, but still each node has a single embedding vector. Furthermore, although GNNs have also been recently applied to HetNets, they are either semi-supervised methods [29], or cannot be applied to a genuine HetNet whose both nodes and edges are multiple typed [18].…”

“…4.4 we defined our primary task as link prediction. In this regard, among various link prediction tasks that can be defined in a HetNet such as, recommendation [10] (i.e., user-item), and author identification (i.e., paper-author), we specifically focus on the task of author identification in big scholarly data whose task is to predict the true authors of an anonymized paper [4,19,32], i.e., link probability between paper-typed nodes and author-typed nodes. Note that each paper is assumed to be associated with its content information.…”