Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https:// github.com/thunlp/MuGNN.

To reduce the dependence on oil and environmental pollution, the development of electric vehicles has been accelerated in many countries. The implementation of EVs, especially battery electric vehicles, is considered a solution to the energy crisis and environmental issues. This paper provides a comprehensive review of the technical development of EVs and emerging technologies for their future application. Key technologies regarding batteries, charging technology, electric motors and control, and charging infrastructure of EVs are summarized. This paper also highlights the technical challenges and emerging technologies for the improvement of efficiency, reliability, and safety of EVs in the coming stages as another contribution.

What prerequisite knowledge should students achieve a level of mastery before moving forward to learn subsequent coursewares? We study the extent to which the prerequisite relation between knowledge concepts in Massive Open Online Courses (MOOCs) can be inferred automatically. In particular, what kinds of information can be leveraged to uncover the potential prerequisite relation between knowledge concepts. We first propose a representation learning-based method for learning latent representations of course concepts, and then investigate how different features capture the prerequisite relations between concepts. Our experiments on three datasets form Coursera show that the proposed method achieves significant improvements (+5.9-48.0% by F1-score) comparing with existing methods.

Entity alignment aims at integrating complementary knowledge graphs (KGs) from different sources or languages, which may benefit many knowledge-driven applications. It is challenging due to the heterogeneity of KGs and limited seed alignments. In this paper, we propose a semi-supervised entity alignment method by joint Knowledge Embedding model and Cross-Graph model (KECG). It can make better use of seed alignments to propagate over the entire graphs with KG-based constraints. Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities. As for the crossgraph model, we extend Graph Attention Network (GAT) with projection constraint to robustly encode graphs, and two KGs share the same GAT to transfer structural knowledge as well as to ignore unimportant neighbors for alignment via attention mechanism. Results on publicly available datasets as well as further analysis demonstrate the effectiveness of KECG. Our codes can be found in https: //github.com/THU-KEG/KECG.

No abstract

To simplify the preparation process of a glucose-responsive microneedle patch, a cross-linking-density changeable microneedle patch was designed. The microneedle patch was made up of a hydrogel formed by phenylboronic acid-grafted polyallylamine and poly­(vinyl alcohol) (PVA). The gel was cross-linked by boronate ester bonds between phenylboronic acid groups and PVA. It still had fluidity and could be filled into a mold to prepare microneedle patches. Moreover, insulin could be directly loaded into the microneedle patch by mixing with the gel. The boronate ester bond would be broken in the presence of glucose, resulting in a decrease in the cross-linking density. Therefore, the gel could achieve a greater swelling degree and insulin could be released faster. In addition, PVA chains were crystallized by repeatedly freezing and thawing to improve the mechanical strength of the microneedle patch. In terms of glucose-dependent insulin release, the gel showed good glucose-responsive insulin-release ability. Through additional ion cross-linking, the microneedle patch could also control the insulin release according to glucose concentration. In the hypoglycemic experiment of diabetic rats, the microneedle patch effectively pierced the skin and slowly released insulin.

No abstract

Joint representation learning of words and entities benefits many NLP tasks, but has not been well explored in cross-lingual settings. In this paper, we propose a novel method for joint representation learning of cross-lingual words and entities. It captures mutually complementary knowledge, and enables cross-lingual inferences among knowledge bases and texts. Our method does not require parallel corpora, and automatically generates comparable data via distant supervision using multi-lingual knowledge bases. We utilize two types of regularizers to align cross-lingual words and entities, and design knowledge attention and crosslingual attention to further reduce noises. We conducted a series of experiments on three tasks: word translation, entity relatedness, and cross-lingual entity linking. The results, both qualitatively and quantitatively, demonstrate the significance of our method.