Neural-Brane: Neural Bayesian Personalized Ranking for Attributed Network Embedding

Abstract

2018. Neural-Brane: Neural Bayesian Personalized Ranking for Attributed Network Embedding. 1, 1 (August 2018), 15 pages. https: //doi.org/10.1145/nnnnnnn.nnnnnnn INTRODUCTIONThe past few years have witnessed a surge in research on embedding the vertices of a network into a low-dimensional, dense vector space. The embedded vector representation of the vertices in such a vector space enables effortless invocation of off-the-shelf machine learning algorithms, thereby facilitating several downstream network mining tasks, including node classification [19], link prediction [8], community detection [21], job recommendation [5], and entity disambiguation [24]. Most existing network embedding methods, including DeepWalk [14], LINE [17], Node2Vec [8], and SDNE [20], utilize the topological information of a network with the rationale that nodes with similar topological roles should be distributed closely in the learned low-dimensional vector space. While this suffices for node embedding of a bare-bone network, it is inadequate for most of today's network datasets which include useful information beyond link connectivity. Specifically, for most of the social and communication networks, a rich set of nodal attributes is typically available, and more importantly, the similarity between a pair of nodes is dictated significantly by the similarity of their attribute values. Yet, the existing embedding models do not provide a principled approach for incorporating nodal attributes into network embedding and thus fail to achieve the performance boost that may be obtained through modeling attribute based nodal similarity. Intuitively, joint network embedding that consider both attributional and relational information could entail complementary information and further enrich the learned vector representations.We provide a few examples from real-life networks to highlight the importance of vertex attributes for understanding the role of the vertices and to predict their interactions. For example, users on social websites contain biographical profiles like age, gender, and textual comments, which dictate who they befriend with, and what are their common interests. In a citation network, each scientific paper is associated with a title, an abstract, and a publication venue, which largely dictates its future citation patterns. In fact, nodal attributes are specifically important when the network topology fails to capture the similarity between a pair of nodes. For example, in academic domain, two researchers who write scientific papers related to "machine learning" and "information retrieval" are not considered to be similar by existing embedding methods (say, DeepWalk or LINE) unless they are co-authors or they share common collaborators. In such a scenario, node attributes of the researchers (e.g., research keywords) are crucial for compensating for the lack of topological similarity between the researchers. In summary, by jointly considering the attribute homophily and the network topology, more informative node representations can be...

Graph Embedding via Graph Summarization

“…[24] proposed a novel Deep Hyper-Network Embedding model to embed hyper-networks with indecomposable hyper-edges to realize a non-linear tuplewise similarity function while preserving both local and global proximities in the formed embedding space. [25] presented a novel neural Bayesian personalized ranking formulation for attributed network embedding, which combines a designed neural network model and a novel Bayesian ranking objective to learn informative vector representations that jointly incorporate network topology and nodal attributions.…”

Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks

“…The user and item feature vectors are computed by a probabilistic linear model with Gaussian observation distribution. Bayesian personalized ranking (BPR) [18] is a generic optimization criterion and learning algorithm for implicit CF and has been widespreadly adopted in many related domains [19], [20], [21], [22].…”

Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art

“…The objective is to minimize the reconstruction loss between the estimated similarity distribution and the ground truth. Dave et al [16] propose Neural-Brane to capture both node attribute information and graph structural information in the embedding of the graph. Bonner et al [6] study the interpretability of graph embedding models.…”