Entity matching (EM) aims to identify whether two entities from different data sources refer to the same real-world entity. Most existing cross-modal EM assume that images have simple scenes containing few objects, or do not fully consider the cross-modal knowledge associated with entities. To support more practical application scenarios such as multi-modal knowledge graph integration and visual question answering in data lakes, we introduce our problem of semantic-driven EM across graph and images in this paper. Current semantically matching solutions over cross-modal data face the obstacle of low training efficiency, since their time complexity quadratically grows with the number of entities. To alleviate this issue, we present a novel framework (namely CrossETR) that follows an exploration-then-refinement paradigm. Firstly, a candidate exploration policy is proposed to boost the training efficiency. It explores candidate pairs according to entity correlations and captures structural semantics by adaptive sampling the most informative neighborhood subgraphs. Secondly, the cross-modal entity representations are refined to break modality heterogeneity to support unsupervised matching prediction. Extensive experimental evaluations on three publicly available benchmarks demonstrate the superiority of CrossETR over state-of-the-art approaches in terms of effectiveness and efficiency. Furthermore, a case study highlights that our proposed semantic-driven EM is promising to improve the performance of downstream tasks such as multi-modal knowledge graph integration.

Time series anomaly detection (TSAD) plays a crucial role in various industrial applications. Traditional deep learning TSAD models require extensive training data and operate as black boxes, lacking interpretability for detected anomalies. To address these challenges, we propose LLMAD, a novel TSAD method that employs Large Language Models (LLMs) to deliver accurate and interpretable TSAD results. LLMAD applies in-context anomaly detection by retrieving both positive and negative similar time series segments, significantly enhancing LLMs' effectiveness. Furthermore, LLMAD employs the Anomaly Detection Chain-of-Thought approach to mimic expert logic for its decision-making process. This further enhances its performance and enables LLMAD to provide explanations for their detections through versatile perspectives.

Cross-source query serves as a proxy for scene understanding to support many web applications such as rec-ommendation systems, e-commerce, and e-learning applications. In this paper, we propose SVQA that semantically combines the knowledge from available images and graphs to answer the complex question. To this end, we design a graph-based method to unify various data sources into one representation. We then develop a complex question parse method that utilizes the structure of languages to transform the query into a query graph. A graph query engine that performs the query graph over the unified data source while optimizing the query process. To evaluate the proposed system, we build a vanilla dataset called MVQA and show that the state-of-the-art (SOTA) VQA models fail to perform our task. The comprehensive evaluations show that the proposed SVQA is able to reason implicit relationships over multiple images and external knowledge to correctly answer a complex query. We hope that our first attempt provides researchers with a fresh taste of multimodal data analysis.