Arijit Khan

Traditional similarity-based schema matching methods fail to resolve semantic ambiguities and conflicts in complex, domain-specific mappings due to a lack of commonsense and domain-specific knowledge. In parallel, large language models (LLMs) without sufficient background knowledge tend to hallucinate, further complicating schema matching. To overcome these limitations, we introduce KG-RAG4SM, a Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching. This method integrates novel retrieval mechanisms, including LLM-based, vector-based, graph traversal-based, and hybrid techniques with advanced reranking schemes to extract the most relevant subgraphs from large external KGs. Our approach achieves superior results without requiring re-training, as evidenced by improvements of 39.79% in precision and 30.56% in F1 score over LLM-based state-of-the-art (SOTA) methods (e.g., Jellyfish-8B) on the MIMIC dataset, and enhancements of 69.20% in precision and 21.99% in F1 score over pre-trained language model (PLM)-based SOTA methods (e.g., SMAT) on the Synthea dataset. Additionally, KG-RAG4SM scales effectively across KGs from commonsense KGs to domain-specific ones, while its instruction-tuning knowledge exclusion component ensures truthful performance in end-to-end schema matching tasks despite the suboptimal relevance of KG context. Our empirical analysis and case studies from real-world scenarios show that the hallucination problem in LLMs for schema matching is well mitigated by our solution.

Correlation Clustering (CC) is a natural formulation of clustering in combinatorial optimization, which uses a graph representation of the input and does not require a pre-specified number of clusters. Given n objects and a pairwise similarity function, the goal is to cluster the objects so that similar objects are put in the same cluster and dissimilar objects are put in different clusters. Despite its versatility, existing CC algorithms suffer from significant scalability issues and are inherently transductive: i.e., the algorithm must be executed from scratch for any new problem instance. In this work, we bridge this gap by leveraging Graph Neural Networks (GNNs) to solve Inductive Correlation Clustering, a novel generalization of the CC problem designed to handle unseen graph instances. By learning to exploit common structural patterns and node features during training, our framework generalizes to new graphs drawn from the same distribution with minimal computational overhead with respect to standard algorithms. We demonstrate the effectiveness and scalability of our approach through extensive experiments. Our framework not only excels in the inductive setting, e.g., lowering the inference time up to 5 order of magnitude, while maintaining an approximation ratio within ~10% of the best baseline solution, but also achieves competitive results on standard (transductive) CC benchmarks. Finally, we showcase a practical application of our framework as a learnable pooling mechanism for graph classification. Our results indicate that our method serves as an efficient pooling layer, enhancing the ability of GNNs to capture hierarchical structural information in networks.

Blockchain technology has rapidly emerged to mainstream attention. At the same time, its publicly accessible, heterogeneous, massive-volume, and temporal data are reminiscent of the complex dynamics encountered during the last decade of big data. Unlike any prior data source, blockchain datasets encompass multiple layers of interactions across real-world entities, e.g., human users, autonomous programs, and smart contracts. Furthermore, blockchain’s integration with cryptocurrencies has introduced financial aspects of unprecedented scale and complexity, such as decentralized finance, stablecoins, non-fungible tokens, and central bank digital currencies. These unique characteristics present opportunities and challenges for machine learning on blockchain data. On the one hand, we examine the state-of-the-art solutions, applications, and future directions associated with leveraging machine learning for blockchain data analysis critical for improving blockchain technology, such as e-crime detection and trends prediction. On the other hand, we shed light on blockchain’s pivotal role by providing vast datasets and tools that can catalyze the growth of the evolving machine learning ecosystem. This article is a comprehensive resource for researchers, practitioners, and policymakers, offering a roadmap for navigating this dynamic and transformative field.

Entity Resolution (ER) is a fundamental data quality improvement task that identifies and links records referring to the same real-world entity. Traditional ER approaches often rely on pairwise comparisons, which can be costly regarding both time and monetary resources, especially when large datasets are involved. Recently, Large Language Models (LLMs) have demonstrated promising results in ER tasks. Still, existing methods typically focus on pairwise matching, missing the potential of LLMs to directly perform clustering in a more cost-effective and scalable manner. In this paper, we propose a novel in-context clustering approach for ER, where LLMs are used to cluster records directly, reducing both time complexity and monetary costs. We systematically investigate the design space for in-context clustering, analyzing the impact of factors such as set size, diversity, variation, and ordering of records on clustering performance. Based on these insights, we develop LLM-CER (LLM-powered Clustering-based ER) that obtains high-quality ER results while minimizing LLM API calls. Our approach addresses key challenges, including efficient cluster merging and LLM's hallucination, providing a scalable and effective solution for ER. Extensive experiments on nine real-world datasets demonstrate that our method significantly improves result quality, achieving up to 150% higher accuracy, 10% increase in the FP-measure, and reducing API calls by up to 5X, while maintaining a comparable monetary cost to the most cost-effective baseline.

Entity Resolution (ER) is a fundamental data quality improvement task that identifies and links records referring to the same real-world entity. Traditional ER approaches often rely on pairwise comparisons, which can be costly in terms of time and monetary resources, especially with large datasets. Recently, Large Language Models (LLMs) have shown promising results in ER tasks. However, existing methods typically focus on pairwise matching, missing the potential of LLMs to perform clustering directly in a more cost-effective and scalable manner. In this paper, we propose a novel in-context clustering approach for ER, where LLMs are used to cluster records directly, reducing both time complexity and monetary costs. We systematically investigate the design space for in-context clustering, analyzing the impact of factors such as set size, diversity, variation, and ordering of records on clustering performance. Based on these insights, we develop LLM-CER (LLM-powered Clustering-based ER), which achieves high-quality ER results while minimizing LLM API calls. Our approach addresses key challenges, including efficient cluster merging and LLM hallucination, providing a scalable and effective solution for ER. Extensive experiments on nine real-world datasets demonstrate that our method significantly improves result quality, achieving up to 150% higher accuracy, 10% increase in the F-measure, and reducing API calls by up to 5 times, while maintaining comparable monetary cost to the most cost-effective baseline.

Traditional similarity-based schema matching methods are incapable of resolving semantic ambiguities and conflicts in domain-specific complex mapping scenarios due to missing commonsense and domain-specific knowledge. The hallucination problem of large language models (LLMs) also makes it challenging for LLM-based schema matching to address the above issues. Therefore, we propose a Knowledge Graph-based Retrieval-Augmented Generation model for Schema Matching, referred to as the KG-RAG4SM. In particular, KG-RAG4SM introduces novel vector-based, graph traversal-based, and query-based graph retrievals, as well as a hybrid approach and ranking schemes that identify the most relevant subgraphs from external large knowledge graphs (KGs). We showcase that KG-based retrieval-augmented LLMs are capable of generating more accurate results for complex matching cases without any re-training. Our experimental results show that KG-RAG4SM outperforms the LLM-based state-of-the-art (SOTA) methods (e.g., Jellyfish-8B) by 35.89% and 30.50% in terms of precision and F1 score on the MIMIC dataset, respectively; KG-RAG4SM with GPT-4o-mini outperforms the pre-trained language model (PLM)-based SOTA methods (e.g., SMAT) by 69.20% and 21.97% in terms of precision and F1 score on the Synthea dataset, respectively. The results also demonstrate that our approach is more efficient in end-to-end schema matching, and scales to retrieve from large KGs. Our case studies on the dataset from the real-world schema matching scenario exhibit that the hallucination problem of LLMs for schema matching is well mitigated by our solution.

Responsible AI is built upon a set of principles that prioritize fairness, transparency, accountability, and inclusivity in AI development and deployment. As AI systems become increasingly sophisticated, including the explosion of generative AI, there is a growing need to address ethical considerations and potential societal impacts of their uses. Knowledge graphs (KGs), as structured representations of information, can enhance generative AI performance by providing context, explaining outputs, and reducing biases, thereby offering a powerful framework to address the challenges of responsible AI. By leveraging semantic relationships and contextual understanding, KGs facilitate transparent decision-making, enabling stakeholders to trace and interpret the reasoning behind AI driven outcomes. Moreover, they provide a means to capture and manage diverse knowledge sources, supporting the development of fair and unbiased AI models. The workshop aims to investigate the role of knowledge graphs in promoting responsible AI principles and creating a cooperative space for researchers, practitioners, and policymakers to exchange insights and enhance their comprehension of KGs' impact on achieving responsible AI solutions. It seeks to facilitate collaboration and idea-sharing to advance the understanding of how KGs can contribute to responsible AI.