Equipping Large Language Models (LLMs) with pedagogical tutoring capabilities holds significant promise for education.Existing approaches simulate tutor behaviors or preferences and use them to prompt or fine-tune LLMs for dialogue tutoring.However, such methods often fail to sustain high-quality pedagogical conversations that provide explicit stepwise scaffolding and adapt to learners' evolving cognitive states.To address this, we propose ScaffoldLM, a planning-guided tutoring framework with an assessment-driven memory for multi-turn math dialogue tutoring.ScaffoldLM first generates a stepwise pedagogical plan from solution steps, which serves as a stable backbone for explicit scaffolding.During tutoring, the tutoring memory is updated by an assessment-driven control loop that infers the learners cognitive state, evaluates whether the current step target is met, and adaptively selects tutoring actions.The plan, step-level progress, inferred learner states, and dialogue history are maintained in memory to support coherent multi-turn guidance.Experiments on multiturn math tutoring benchmarks demonstrate that ScaffoldLM substantially improves pedagogical tutoring quality over strong baselines.Code is publicly available

Product search is crucial for customers to discover and purchase products. With the growing importance of AI explanations, many KG-based methods use independent reasoning paths to provide explanations for retrieved results. However, these methods often fail to relate explanations to the current query and provide only single-facet explanations rather than multi-facet explanations that address users’ diverse search intents, such as different categories or bands. To overcome this issue, we propose an explainable product search model QGCNM, to generate query-aware multi-facet explanations through hierarchical graph convolution. Specifically, we design a query-aware graph convolutional ranker to excavate user’s multi-aspect search intent and develop a multi-path reasoner to explore the intent-based multiple paths for multi-facet explanations. Empirical evaluations on Amazon datasets show that QGCNM outperforms existing models on retrieval effectiveness and has better explanation abilities.

Catastrophic forgetting is a key challenge in incremental named entity recognition (INER). Existing methods often address this issue through distillation-based approaches, which involve transferring previously learned knowledge from the old model to the new one. However, these methods may not fully equip the new model with an adequate understanding of the characteristics about old entity types, leading to confusion when classifying tokens associated with these entity types. To address this challenge, we propose a novel method called Prototypical Replay with Old-class Focusing Knowledge Distillation (POF) for INER. Our approach focuses on preserving the main characteristics of each previous entity type by storing compact prototypes and replaying them with appropriate frequency. This replay strategy makes the new model review the knowledge of old entity types while minimizing storage needs. Additionally, we introduce an old-class focusing knowledge distillation (OFKD) loss, which distills features only in old-class regions to maintain the quality of old-class prototypes and prevent ineffective prototypical replay while preserving sufficient plasticity for learning new entity types. We conducted experiments on three benchmark datasets (i.e., Few-NERD, I2B2 and OntoNotes5), and the results demonstrate that our method outperforms all previous state-of-the-art methods.

Federated learning-based Named Entity Recognition (FNER) has attracted widespread attention through decentralized training on local clients. However, most FNER models assume that entity types are pre-fixed, so in practical applications, local clients constantly receive new entity types without enough storage to access old entity types, resulting in severe forgetting on previously learned knowledge. In addition, new clients collecting only new entity types may join the global training of FNER irregularly, further exacerbating catastrophic forgetting. To overcome the above challenges, we propose a Forgetting-Subdued Learning (FSL) model which solves the forgetting problem on old entity types from both intra-client and inter-client two aspects. Specifically, for intra-client aspect, we propose a prototype-guided adaptive pseudo labeling and a prototypical relation distillation loss to surmount catastrophic forgetting of old entity types with semantic shift. Furthermore, for inter-client aspect, we propose a task transfer detector. It can identify the arrival of new entity types that are protected by privacy and store the latest old global model for relation distillation. Qualitative experiments have shown that our model has made significant improvements compared to several baseline methods.

Recently, large language models (LLMs) have shown the potential to enhance recommendations due to their sufficient knowledge and remarkable summarization ability. However, the existing LLM-powered recommendation may create redundant output, which generates irrelevant information about the user’s preferences on candidate items from user behavior sequences. To address the issues, we propose a framework UR4Rec that enhances reranking for recommendation with large language models through user preference retrieval. Specifically, UR4Rec develops a small transformer-based user preference retriever towards candidate items to build the bridge between LLMs and recommendation, which focuses on producing the essential knowledge through LLMs from user behavior sequences to enhance reranking for recommendation. Our experimental results on three real-world public datasets demonstrate the superiority of UR4Rec over existing baseline models.

Temporal Knowledge Graphs (TKGs) are being widely explored to predict the future for they record multi-relational knowledge and the happening time of real-life facts. Existing works learn sequential patterns to infer the future from past facts in TKGs for predictions. Although achieving promising results, they are restricted by the sequential modeling in both efficiency and effectiveness. To resolve these limitations, we propose our efficient and effective non-sequential relational modeling (NoSeq). NoSeq works non-sequentially for temporal patterns where it transforms the happening time into time intervals. Time intervals are the period of time between happening time and prediction time which state the temporal distance clearly. Both time intervals and relations are represented using embeddings and merged non-sequentially into entity embeddings for future predictions. We evaluate NoSeq on four datasets from the perspective of effectiveness, efficiency, sensitivity, and the ability to transfer. Consistent better performances verify our idea.

Temporal Knowledge Graphs (TKGs) represent real-life facts using entities, relational types, and timestamps where relational types state the semantic scenario of facts. Current methods learn embeddings by merging facts of multiple types (e.g. sport and family) for predictions. Such embeddings associate well with relations of multiple types. However, the prediction needs only information of a single type, i.e. embeddings contain irrelevant relational types. In this paper, we explore whether embeddings with irrelevant information confuse predictions and propose RefE to improve embeddings by refining meanings. RefE enhances the ability for predicting links of a specific type while maintaining associations of multiple relational types. RefE consists of general learning and embedding refining modules. General learning embeds facts of multiple types to represent general meanings, and embedding refining emphasizes facts of the single type that matches the prediction. RefE uses both general and refined embeddings for predictions. Experimental results on four datasets verify the effectiveness of RefE.

User behavior records serve as the foundation for recommender systems. While the behavior data exhibits ease of acquisition, it often suffers from varying quality. Current methods employ data valuation to discern high-quality data from low-quality data. However, they tend to employ blackbox design, lacking transparency and interpretability. Besides, they are typically tailored to specific evaluation metrics, leading to limited generality across various tasks. To overcome these issues, we propose an explainable and versatile framework DVR which can enhance the efficiency of data utilization tailored to any requirements of the model architectures and evaluation metrics. For explainable data valuation, a data valuator is presented to evaluate the data quality via calculating its Shapley value from the game-theoretic perspective, ensuring robust mathematical properties and reliability. In order to accommodate various evaluation metrics, including differentiable and non-differentiable ones, a metric adapter is devised based on reinforcement learning, where a metric is treated as the reinforcement reward that guides model optimization. Extensive experiments conducted on various benchmarks verify that our framework can improve the performance of current recommendation algorithms on various metrics including ranking accuracy, diversity, and fairness. Specifically, our framework achieves up to 34.7% improvements over existing methods in terms of representative NDCG metric. The code is available at https://github.com/renqii/DVR.

With the increasing integration of renewable energy into power grids, integrated energy systems (IES) have gained global attention. However, the stochastic and uncertain characteristics of wind and solar challenge the stable grid operation significantly. To address these issues, this article proposes an optimal scheduling model for wind-solar-hydrogen IES, incorporating prediction uncertainty and demand response (DR). The equilibrium decision theory framework, combined with frequency enhanced decomposed transformer, interval prediction and decision, is proposed to quantify the uncertainties and determine the action plans. Then, an optimal scheduling model is designed to maximize economic revenue and minimize pollution emissions (PE), which is solved using multiobjective elephant clan optimization algorithm. Furthermore, DR strategy is integrated to enhance system flexibility and stability. Empirical results demonstrate that increased uncertainty leads to more conservative scheduling, improving system robustness. Additionally, DR boosts ER by over 3.50% and reduces PE by more than 3.20% across various scenarios.

Product search is crucial for users to find and purchase products they need. Personalized product search, which models users’ search intent and provides tailored results, has become a prominent research problem in industry and academia. Recent studies often leverage knowledge graphs (KGs) to improve search performance and generate explanations for search results. However, existing KG-based methods treat search and explanation tasks separately and explore paths in KGs as explanations, creating a gap between search results and generated explanations. Also, path-formed explanations in KGs are not flexible enough to build correlations with the user’s current query. To address these challenges, we propose P-PEG, a unified prompt-aware framework for personalized product search and explanation generation. P-PEG leverages a pre-trained language model (PLM) and search signal to enhance the generation of user-understandable explanations. We introduce a prompt learning technique and design prompt generators for search and explanation generation tasks based on a fixed PLM. By incorporating search results in explanation-based prompts, we bridge the gap between search results and explanations, facilitating better interaction. Additionally, we utilize the user’s current query, historical search log, and KGs to personalize the explanations and inject task knowledge into PLM. Experimental results show that P-PEG outperforms existing methods in the explanation generation task of the three datasets and the search task of the Electronics dataset, and achieves comparable performance in the search task of the Cellphones & Accessories and CD & Vinyl datasets.

Cold-start is a significant problem in recommender systems. Recently, with the development of few-shot learning and meta-learning techniques, many researchers have devoted themselves to adopting meta-learning into recommendation as the natural scenario of few-shots. Nevertheless, we argue that recent work has a huge gap between few-shot learning and recommendations. In particular, users are locally dependent, not globally independent in recommendation. Therefore, it is necessary to formulate the local relationships between users. To accomplish this, we present a novel Few-shot learning method for Cold-Start (FCS) recommendation that consists of three hierarchical structures. More concretely, this first hierarchy is the global-meta parameters for learning the global information of all users; the second hierarchy is the local-meta parameters whose goal is to learn the adaptive cluster of local users; the third hierarchy is the specific parameters of the target user. Both the global and local information are formulated, addressing the new user’s problem in accordance with the few-shot records rapidly. Experimental results on two public real-world datasets show that the FCS method could produce stable improvements compared with the state-of-the-art.

Traditional search engines usually provide identical search results for all users, overlooking individual preferences. To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query logs. Deep learning-based personalized search methods have shown promise, but they rely heavily on abundant training data, making them susceptible to data sparsity challenges. This paper proposes a Cognitive Personalized Search (CoPS) model, which integrates Large Language Models (LLMs) with a cognitive memory mechanism inspired by human cognition. CoPS employs LLMs to enhance user modeling and user search experience. The cognitive memory mechanism comprises sensory memory for quick sensory responses, working memory for sophisticated cognitive responses, and long-term memory for storing historical interactions. CoPS handles new queries using a three-step approach: identifying re-finding behaviors, constructing user profiles with relevant historical information, and ranking documents based on personalized query intent. Experiments show that CoPS outperforms baseline models in zero-shot scenarios.

Product search is one of the most effective tools for people to browse and purchase products on e-commerce platforms. Recent advances have mainly focused on ranking products by their likelihood to be purchased through retrieval models. However, they overlook the problem that users may not understand why certain products are retrieved for them. The lack of appropriate explanations can lead to an unsatisfactory user experience and further decrease user trust in the platforms. To address this problem, we propose a Query-aware Explainable Product Search with Reinforcement Knowledge Reasoning, namelyQEPS, which uses search behaviors related to the current query to reinforce explanations. Specifically, with the aim of retrieving suitable products with explanations, QEPS takes full advantage of the user-product knowledge graph (KG) and develops a reinforcement learning approach, characterized by the demonstration-guided policy network and query-aware rewards, to perform explicit multi-step reasoning on the KG. The reasoning paths between users and products are automatically derived from the current query-related search behavior, which can provide valuable signals as to why the retrieved products are more likely to satisfy the user's search intent. Empirical experiments on four datasets show that our model achieves remarkable performance and is able to generate reasonable explanations for the search results.

Ambiguity in queries is a common problem in information retrieval. There are currently two solutions: search result personalization and diversification. The former aims to tailor results for different users based on their preferences, but the limitations are redundant results and incomplete capture of user intents. The goal of the latter is to return results that cover as many aspects related to the query as possible. It improves diversity yet loses personality and cannot return the exact results the user wants. Intuitively, such two solutions can complement each other and bring more satisfactory reranking results. In this article, we propose a novel framework, namely, PnD , to integrate personalization and diversification reasonably. We employ the degree of refinding to determine the weight of personalization dynamically. Moreover, to improve the diversity and relevance of reranked results simultaneously, we design a reset RNN structure (RRNN) with the “reset gate” to measure the influence of the newly selected document on novelty. Besides, we devise a “subtopic learning layer” to learn the virtual subtopics, which can yield fine-grained representations of queries, documents, and user profiles. Experimental results illustrate that our model can significantly outperform existing search result personalization and diversification methods.

Knowledge graphs (KGs) have been widely used in recommendation systems to improve recommendation accuracy and interpretability effectively. Recent research usually endows KG reasoning to find the multi-hop user-item connection paths for explaining why an item is recommended. The existing path-finding process is well designed by logic-driven inference algorithms, while there exists a gap between how algorithms and users perceive the reasoning process. Factually, human thinking is a natural reasoning process that can provide more proper and convincing explanations of why particular decisions are made. Motivated by the Dual Process Theory in cognitive science, we propose a cognition-aware KG reasoning model CogER for Explainable Recommendation, which imitates the human cognition process and designs two modules, i.e., System~1 (making intuitive judgment) and System~2 (conducting explicit reasoning), to generate the actual decision-making process. At each step during the cognition-aware reasoning process, System~1 generates an intuitive estimation of the next-step entity based on the user's historical behavior, and System~2 conducts explicit reasoning and selects the most promising knowledge entities. These two modules work iteratively and are mutually complementary, enabling our model to yield high-quality recommendations and proper reasoning paths. Experiments on three real-world datasets show that our model achieves better recommendation results with explanations compared with previous methods.

Recent studies show that historical behaviors (such as queries and their clicks) contained in a search session can benefit the ranking performance of subsequent queries in the session. Existing neural context-aware ranking models usually rank documents based on either latent representations of user search behaviors or the word-level interactions between the candidate document and each historical behavior in the search session. However, these two kinds of models both have their own drawbacks. Representation-based models neglect fine-grained information on word-level interactions, whereas interaction-based models suffer from the length restriction of session sequence because of the large cost of word-level interactions. To complement the limitations of these two kinds of models, we propose a unified context-aware document ranking model that takes full advantage of both representation and interaction. Specifically, instead of matching a candidate document with every single historical query in a session, we encode the session history into a latent representation and use this representation to enhance the current query and the candidate document. We then just match the enhanced query and candidate document with several matching components to capture the fine-grained information of word-level interactions. Rich experiments on two public query logs prove the effectiveness and efficiency of our model for leveraging representation and interaction.

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r, ?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k-237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https://github.com/renli1024/SE-GNN.

Knowledge graph (KG) entity typing focuses on inferring possible entity type instances, which is a significant subtask of knowledge graph completion (KGC). Existing entity typing methods usually exploit the entity representation to model the transmission between entities and their types, which cannot fully explore the fine-grained entity typing on identifying the semantic type of an entity. To address these issues, we propose Neighborhood-Attention Neural Fine-Grained Entity Typing (AttEt), which considers the neighborhood information of the entities from KGs to bridge entities and their types together. In this paper, AttEt first develops a type-specific attention mechanism to aggregate the neighborhood knowledge of the given entity with type-specific weights. These weights are beneficial to capture various characteristics for different types of the entity, and further imply the complex correlation among these fine-grained types. Then, AttEt adaptively integrates the aggregated neighbor-level representation with entity inherent embedding to calculate the matching score between the entity and its candidate type. Besides, many entities are sparse in their relations with other entities in KGs, which makes the entity typing task more challenging. To solve this problem, we present a smooth strategy on relation-sparsity entities to improve the robustness of the model. Extensive experiments on two real-world datasets (Freebase and YAGO) show that AttEt significantly outperforms state-of-the-art baselines in the [email protected] by 2.11% on Freebase and by 8.42% on YAGO, respectively.

Product search has been an important way for people to find products on online shopping platforms. Existing approaches in personalized product search mainly embed user preferences into one single vector. However, this simple strategy easily results in sub-optimal representations, failing to model and disentangle user’s multiple preferences. To overcome this problem, we proposed a category-aware multi-interest model to encode users as multiple preference embeddings to represent user-specific interests. Specifically, we also capture the category indications for each preference to indicate the distribution of categories it focuses on, which is derived from rich relations between users, products, and attributes. Based on these category indications, we develop a category attention mechanism to aggregate these various preference embeddings considering current queries and items as the user’s comprehensive representation. By this means, we can use this representation to calculate matching scores of retrieved items to determine whether they meet the user’s search intent. Besides, we introduce a homogenization regularization term to avoid the redundancy between user interests. Experimental results show that the proposed method significantly outperforms existing approaches.

Selecting reliable negative training instances is the challenging task in the implicit feedback-based recommendation, which is optimized by pairwise learning on user feedback data. The existing methods usually exploit various negative samplers (i.e., heuristic-based or GAN-based sampling) on user feedback data to improve the quality of negative samples. However, these methods usually focused on maintaining the hard negative samples with a high gradient for training, causing the false negative samples to be selected preferentially. The limitation of the false negative noise amplification may lead to overfitting and further poor generalization of the model. To address this issue, we propose a Gain-Tuning Dynamic Negative Sampling GDNS to make the recommendation more robust and effective. Our proposed model designs an expectational gain sampler, concerning the expectation of user’ preference gap between the positive and negative samples in training, to guide the negative selection dynamically. This gain-tuning negative sampler can effectively identify the false negative samples and further diminish the risk of introducing false negative instances. Moreover, for improving the training efficiency, we construct positive and negative groups for each user in each iteration, and develop a group-wise optimizer to optimize them in a cross manner. Experiments on two real-world datasets show our approach significantly outperforms state-of-the-art negative sampling baselines.

The core objective of modelling recommender systems from implicit feedback is to maximize the positive sample score sp and minimize the negative sample score sn, which can usually be summarized into two paradigms: the pointwise and the pairwise. The pointwise approaches fit each sample with its label individually, which is flexible in weighting and sampling on instance-level but ignores the inherent ranking property. By qualitatively minimizing the relative score sn − sp, the pairwise approaches capture the ranking of samples naturally but suffer from training efficiency. Additionally, both approaches are hard to explicitly provide a personalized decision boundary to determine if users are interested in items unseen. To address those issues, we innovatively introduce an auxiliary score bu for each user to represent the User Interest Boundary(UIB) and individually penalize samples that cross the boundary with pairwise paradigms, i.e., the positive samples whose score is lower than bu and the negative samples whose score is higher than bu. In this way, our approach successfully achieves a hybrid loss of the pointwise and the pairwise to combine the advantages of both. Analytically, we show that our approach can provide a personalized decision boundary and significantly improve the training efficiency without any special sampling strategy. Extensive results show that our approach achieves significant improvements on not only the classical pointwise or pairwise models but also state-of-the-art models with complex loss function and complicated feature encoding.

Knowledge graph embedding is an effective way to represent knowledge graph, which greatly enhance the performances on knowledge graph completion tasks, e.g., entity or relation prediction. For knowledge graph embedding models, designing a powerful loss framework is crucial to the discrimination between correct and incorrect triplets. Margin-based ranking loss is a commonly used negative sampling framework to make a suitable margin between the scores of positive and negative triples. However, this loss can not ensure ideal low scores for the positive triplets and high scores for the negative triplets, which is not beneficial for knowledge completion tasks. In this paper, we present a double limit scoring loss to separately set upper bound for correct triplets and lower bound for incorrect triplets, which provides more effective and flexible optimization for knowledge graph embedding. Upon the presented loss framework, we present several knowledge graph embedding models including TransE-SS, TransH-SS, TransD-SS, ProjE-SS and ComplEx-SS. The experimental results on link prediction and triplet classification show that our proposed models have the significant improvement compared to state-of-the-art baselines.

Recurrent neural network(RNN) has achieved remarkable performances in complex reasoning on knowledge bases, which usually takes as inputs vector embeddings of relations along a path between an entity pair. However, it is insufficient to extract local correlations of a path due to RNN is better at capturing global sequential information of a path. In this paper, we take full advantages of convolutional neural network that can effectively extract local features, and propose a convolutional-based RNN architecture denoted as C-RNN to perform reasoning. C-RNN first utilizes CNN to extract local high-level correlation features of a path, and then feeds the correlation features into recurrent neural network to model the path representation. Our C-RNN architecture is adaptable to obtain not only local features but also global sequential features of a path. Based on C-RNN architecture, we devise two models, the unidirectional C-RNN and bidirectional C-RNN. We empirically evaluate them on a large-scale FreeBase+ClueWeb prediction task. Experimental results show that C-RNN models achieve state-of-the-art predictive performance.

Knowledge-graph-aware recommendation systems have increasingly attracted attention in both industry and academic recently. Many existing knowledge-aware recommendation methods have achieved better performance, which usually perform recommendation by reasoning on the paths between users and items in knowledge graphs. However, they ignore the users' personal clicked history sequences that can better reflect users' preferences within a period of time for recommendation. In this paper, we propose a knowledge-aware attentional reasoning network KARN that incorporates the users' clicked history sequences and path connectivity between users and items for recommendation. The proposed KARN not only develops an attention-based RNN to capture the user's history interests from the user's clicked history sequences, but also a hierarchical attentional neural network to reason on paths between users and items for inferring the potential user intents on items. Based on both user's history interest and potential intent, KARN can predict the clicking probability of the user with respective to a candidate item. We conduct experiment on Amazon review dataset, and the experimental results demonstrate the superiority and effectiveness of our proposed KARN model.

Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts. This is a big challenge due to some of the triplets extracted from one sentence may have overlapping entities. Most existing methods perform entity recognition followed by relation detection between every possible entity pairs, which usually suffers from numerous redundant operations. In this paper, we propose a relation-specific attention network (RSAN) to handle the issue. Our RSAN utilizes relation-aware attention mechanism to construct specific sentence representations for each relation, and then performs sequence labeling to extract its corresponding head and tail entities. Experiments on two public datasets show that our model can effectively extract overlapping triplets and achieve state-of-the-art performance.

With the rapid information explosion of news, making personalized news recommendation for users becomes an increasingly challenging problem. Many existing recommendation methods that regard the recommendation procedure as the static process, have achieved better recommendation performance. However, they usually fail with the dynamic diversity of news and user’s interests, or ignore the importance of sequential information of user’s clicking selection. In this paper, taking full advantages of convolution neural network (CNN), recurrent neural network (RNN) and attention mechanism, we propose a deep attention neural network DAN for news recommendation. Our DAN model presents to use attention-based parallel CNN for aggregating user’s interest features and attention-based RNN for capturing richer hidden sequential features of user’s clicks, and combines these features for new recommendation. We conduct experiment on real-world news data sets, and the experimental results demonstrate the superiority and effectiveness of our proposed DAN model.

Multilingual knowledge graphs constructed by entity alignment are the indispensable resources for numerous AI-related applications. Most existing entity alignment methods only use the triplet-based knowledge to find the aligned entities across multilingual knowledge graphs, they usually ignore the neighborhood subgraph knowledge of entities that implies more richer alignment information for aligning entities. In this paper, we incorporate neighborhood subgraph-level information of entities, and propose a neighborhood-aware attentional representation method NAEA for multilingual knowledge graphs. NAEA devises an attention mechanism to learn neighbor-level representation by aggregating neighbors' representations with a weighted combination. The attention mechanism enables entities not only capture different impacts of their neighbors on themselves, but also attend over their neighbors' feature representations with different importance. We evaluate our model on two real-world datasets DBP15K and DWY100K, and the experimental results show that the proposed model NAEA significantly and consistently outperforms state-of-the-art entity alignment models.

In knowledge graph embedding models, the margin-based ranking loss as the common loss function is usually used to encourage discrimination between golden triplets and incorrect triplets, which has proved effective in many translation-based models for knowledge graph embedding. However, we find that the loss function cannot ensure the fact that the scoring of correct triplets must be low enough to fulfill the translation. In this paper, we present a limit-based scoring loss to provide lower scoring of a golden triplet, and then to extend two basic translation models TransE and TransH, separately to TransE-RS and TransH-RS by combining limit-based scoring loss with margin-based ranking loss. Both the presented models have low complexities of parameters benefiting for application on large scale graphs. In experiments, we evaluate our models on two typical tasks including triplet classification and link prediction, and also analyze the scoring distributions of positive and negative triplets by different models. Experimental results show that the introduced limit-based scoring loss is effective to improve the capacities of knowledge graph embedding.