No abstract

Nodes in a multiplex network are connected by multiple types of relations. However, most existing network embedding methods assume that only a single type of relation exists between nodes. Even for those that consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph. We present a simple yet effective unsupervised network embedding method for attributed multiplex network called DMGI, inspired by Deep Graph Infomax (DGI) that maximizes the mutual information between local patches of a graph, and the global representation of the entire graph. We devise a systematic way to jointly integrate the node embeddings from multiple graphs by introducing 1) the consensus regularization framework that minimizes the disagreements among the relation-type specific node embeddings, and 2) the universal discriminator that discriminates true samples regardless of the relation types. We also show that the attention mechanism infers the importance of each relation type, and thus can be useful for filtering unnecessary relation types as a preprocessing step. Extensive experiments on various downstream tasks demonstrate that DMGI outperforms the state-of-the-art methods, even though DMGI is fully unsupervised.

The emergence of a plant vascular system was a prerequisite for the colonization of land; however, it is unclear how the photosynthate transporting system was established during plant evolution. Here, we identify a novel translational regulatory module for phloem development involving the zinc-finger protein JULGI (JUL) and its targets, the 5' untranslated regions (UTRs) of the SUPPRESSOR OF MAX2 1-LIKE4/5 (SMXL4/5) mRNAs, which is exclusively conserved in vascular plants. JUL directly binds and induces an RNA G-quadruplex in the 5' UTR of SMXL4/5, which are key promoters of phloem differentiation. We show that RNA G-quadruplex formation suppresses SMXL4/5 translation and restricts phloem differentiation. In turn, JUL deficiency promotes phloem formation and strikingly increases sink strength per seed. We propose that the translational regulation by the JUL/5' UTR G-quadruplex module is a major determinant of phloem establishment, thereby determining carbon allocation to sink tissues, and that this mechanism was a key invention during the emergence of vascular plants.

No abstract

Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learningbased approaches have been proposed to overcome this issue, existing approaches typically project each user to a single point in the metric space, and thus do not suffice for properly modeling the intensity and the heterogeneity of user-item relationships in implicit feedback. In this paper, we propose TransCF to discover such latent user-item relationships embodied in implicit user-item interactions. Inspired by the translation mechanism popularized by knowledge graph embedding, we construct useritem specific translation vectors by employing the neighborhood information of users and items, and translate each user toward items according to the user's relationships with the items. Our proposed method outperforms several state-of-the-art methods for top-N recommendation on seven real-world data by up to 17% in terms of hit ratio. We also conduct extensive qualitative evaluations on the translation vectors learned by our proposed method to ascertain the benefit of adopting the translation mechanism for implicit feedback-based recommendations.