Link prediction in simple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is need to model relationships among vertices which go beyond pairwise associations. For example, in a chemical reaction, relationship among the reactants and products is inherently higherorder. Additionally, there is need to represent the direction from reactants to products. Hypergraphs provide a natural way to represent such complex higher-order relationships. Graph Convolutional Networks (GCN) have recently emerged as a powerful deep learning-based approach for link prediction over simple graphs. However, their suitability for link prediction in hypergraphs is underexplored-we fill this gap in this paper and propose Neural Hyperlink Predictor (NHP). NHP adapts GCNs for link prediction in hypergraphs. We propose two variants of NHP-NHP-U and NHP-D-for link prediction over undirected and directed hypergraphs, respectively. To the best of our knowledge, NHP-D is the first ever method for link prediction over directed hypergraphs. An important feature of NHP is that it can also be used for hyperlinks in which dissimilar vertices interact (e.g. acids reacting with bases). Another attractive feature of NHP is that it can be used to predict unseen hyperlinks at test time (inductive hyperlink prediction). Through extensive experiments on multiple real-world datasets, we show NHP's effectiveness. CCS CONCEPTS • Computing methodologies → Neural networks; Unsupervised learning.

Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context of a word, such methods result in an explosion of the vocabulary size. In this paper, we overcome this problem by proposing SynGCN, a flexible Graph Convolution based method for learning word embeddings. SynGCN utilizes the dependency context of a word without increasing the vocabulary size. Word embeddings learned by SynGCN outperform existing methods on various intrinsic and extrinsic tasks and provide an advantage when used with ELMo. We also propose SemGCN, an effective framework for incorporating diverse semantic knowledge for further enhancing learned word representations. We make the source code of both models available to encourage reproducible research.

Stability of the anode catalysts for PEM water electrolysers can be substantially improved by combining the catalytic component with antimony oxides. However, the mechanisms of the catalyst stabilisation differ depending on the active element used.

With a motivation to discover efficient materials for direct electrolysis of seawater, bimetallic oxy-boride (Co−Fe−O− B) nanostructures were developed using a facile hydrothermal synthesis strategy, with varying content of Fe. The oxygen evolution performance of the optimized Co−Fe−O−B catalyst in alkali water (1 M KOH) showed higher reaction rates owing to a Co 3 O 4 −core−Co 2 B-shell structure, which assists in the formation of active CoOOH species at lower potentials and offers a smaller charge-transfer resistance. The best-performing catalyst in alkali water was found to be highly active (294 mV to achieve 10 mA/ cm 2 ) in saline water (1 M KOH + 0.5 M NaCl), with 100% O 2 selectivity, establishing its potential for seawater electrolysis. The high activity and selectivity of the oxy-boride catalyst in alkaline saline electrolyte presents a fresh avenue for research in low-cost materials, especially boron-containing compounds, for selective seawater splitting.

No abstract