Entity alignment (EA) is crucial for integrating knowledge graphs (KGs) constructed from diverse sources. Conventional unsupervised EA approaches attempt to eliminate human intervention but often suffer from accuracy limitations. With the rise of large language models (LLMs), leveraging their capabilities for EA presents a promising direction. However, it introduces new challenges: formulating the LLM-based EA problem and extracting the background knowledge in LLMs to realize EA without human intervention. This paper proposes HLMEA, a novel hybrid language model-based unsupervised EA method. HLMEA formulates the EA task into a filtering and single-choice problem and synergistically integrates small language models (SLMs) and LLMs. Specifically, SLMs filter candidate entities based on textual representations generated from KG triples. Then, LLMs refine this selection to identify the most semantically aligned entities. An iterative self-training mechanism allows SLMs to distill knowledge from LLM outputs, enhancing the EA ability of hybrid language models in subsequent rounds cooperatively. We also conducted extensive experiments on benchmark datasets to evaluate HLMEA's performance. The results demonstrate that HLMEA significantly outperforms unsupervised and even supervised EA baselines, proving its potential for scalable and effective EA across large KGs. The code and data are available at \url{https://github.com/xnjin-ai/HLMEA}.
In the context of the continuous development of the Internet, crowdsourcing has received continuous attention as a new cooperation model based on the relationship between enterprises, the public and society. Among them, a reasonably designed recommendation algorithm can recommend a batch of suitable workers for crowdsourcing tasks to improve the final task completion quality. Therefore, this paper proposes a crowdsourcing recommendation framework based on workers’ influence (CRBI). This crowdsourcing framework completes the entire process design from task distribution, worker recommendation, and result return through processes such as worker behavior analysis, task characteristics construction, and cost optimization. In this paper, a calculation model of workers’ influence characteristics based on the ablation method is designed to evaluate the comprehensive performance of workers. At the same time, the CRBI framework combines the traditional open-call task selection mode, builds a new task characteristics model by sensing the influence of the requesting worker and its task performance. In the end, accurate worker recommendation and task cost optimization are carried out by calculating model familiarity. In addition, for recommending workers to submit task answers, this paper also proposes an aggregation algorithm based on weighted influence to ensure the accuracy of task results. This paper conducts simulation experiments on some public datasets of AMT, and the experimental results show that the CRBI framework proposed in this paper has a high comprehensive performance. Moreover, CRBI has better usability, more in line with commercial needs, and can well reflect the wisdom of group intelligence.
Relation extraction tasks aim to predict potential relations between entities in a target sentence. As entity mentions have ambiguity in sentences, some important contextual information can guide the semantic representation of entity mentions to improve the accuracy of relation extraction. However, most existing relation extraction models ignore the semantic guidance of contextual information to entity mentions and treat entity mentions in and the textual context of a sentence equally. This results in low-accuracy relation extractions. To address this problem, we propose a contextual semantic-guided entity-centric graph convolutional network (CEGCN) model that enables entity mentions to obtain semantic-guided contextual information for more accurate relational representations. This model develops a self-attention enhanced neural network to concentrate on the importance and relevance of different words to obtain semantic-guided contextual information. Then, we employ a dependency tree with entities as global nodes and add virtual edges to construct an entity-centric logical adjacency matrix (ELAM). This matrix can enable entities to aggregate the semantic-guided contextual information with a one-layer GCN calculation. The experimental results on the TACRED and SemEval-2010 Task 8 datasets show that our model can efficiently use semantic-guided contextual information to enrich semantic entity representations and outperform previous models.
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Negative transfer (NF) is a critical challenge in personalized federated learning (pFL). Existing methods primarily focus on adapting local data distribution on the client side, which can only resist NF, rather than avoid NF itself. To tackle NF at its root, we investigate its mechanism through the lens of the global model, and argue that it is caused by update conflicts among clients during server aggregation. In light of this, we propose a conflict-free client update aggregation strategy (ConFREE), which enables us to avoid NF in pFL. Specifically, ConFREE guides the global update direction by constructing a conflict-free guidance vector through projection and utilizes the optimal local improvements of the worst-performing clients near the guidance vector to regularize server aggregation. This prevents the conflicting components of updates from transferring, achieving balanced updates across different clients. Notably, ConFREE is model-agnostic and can be straightforwardly adopted as a complement to enhance various existing NF-resistance methods implemented on the client side. Extensive experiments demonstrate substantial improvements to existing pFL algorithms by leveraging ConFREE.