Data spaces are an emerging concept with significant potential to enable a data-centric economy by fostering seamless and secure data sharing across diverse stakeholders. These environments are designed to unlock the value of data by ensuring interoperability and collaboration, which are essential for innovation and informed decision-making. However, managing access control in data spaces poses unique challenges, as it must account for complex relationships not only among stakeholders but also among data items themselves, requiring a flexible and context-aware approach. To this end, in this paper we present the design, implementation, and evaluation of an access control solution tailored for data spaces. Our solution leverages the paradigm of Relationship-Based Access Control (ReBAC), enabling the definition and enforcement of access control policies that consider the relationships between entities within the data space, as well as data consumer organisational structures. Furthermore, we propose a distributed version of our solution to facilitate the segregation of access control management across different administrative domains. Our approach supports fine-grained, continuous access control by dynamically evaluating the context of both the protected data items and the consumers of the data space. To ensure compatibility with existing data-sharing standards, we have integrated our solution with ETSI NGSI-LD API, a standardised interface for interacting with data spaces.

Abstract Data spaces have recently emerged as an innovative paradigm for cross-organizational data sharing. These decentralized environments require sophisticated data governance protocols to ensure compliance with data standards, roles and policies. While current policy-based solutions address enforcement of data access control and usage rights, they lack mechanisms for automated data validation -essential for ensuring data quality for collaborative analytics. To address this gap, we present a knowledge graph-based framework to automate data validation inline with data policies. This framework relies on the concept of policy checkers, which represent high-level and technology-agnostic data validation plans that can be dynamically translated into technology-specific user defined functions (UDFs) for compliance checking. Importantly, the usage of knowledge graphs to describe the policy checkers enhances the transparency and traceability of data validation processes, while the two-stage process (technology-agnostic policy checkers and technology-specific UDFs) accommodate data validation on multimodal data. We accompany the description of our approach with a proof of concept that demonstrates the feasibility of this solution in real data spaces.

Abstract Discovering relevant datasets in large, heterogeneous data ecosystems, such as Data Lakes or Data spaces, is a complex task, often hindered by a lack of transparency and user-centric explanations in the discovery process. Explainability is critical for enabling users to understand why specific datasets are recommended, what information they contain, and how they align with user-defined criteria and preferences. To address these challenges, this work proposes a novel Graph Retrieval-Augmented Generation (Graph RAG) framework to enhance explainability in a platform for discovery of summary data sources. The proposed approach leverages a Knowledge Graph (KG) to interpret user requests, extracting relevant contextual information. These enriched requests are then transformed by a Large Language Model (LLM) into actionable dataset queries for a dataset discovery platform. Candidate solutions are evaluated and enriched with statistical insights on value distributions and contextual knowledge from the KG. Finally, the LLM ranks these solutions based on user preferences, producing a final report. This dual strategy of query enrichment and contextual explanation fosters transparency and enhances user understanding of the discovery process. We demonstrate the effectiveness of the approach through an experimental validation, highlighting its potential to improve both the accuracy and interpretability of dataset discovery.

Abstract Human beings capable of making and using tools can accomplish tasks far beyond their innate abilities, and this paradigm of integration with tools may not be limited to humans themselves. Recently, the large language model (LLM) has demonstrated immense potential across various fields with its unique planning and reasoning abilities. However, there are still many challenges beyond its capabilities due to deficiencies in its training data and inherent illusions. Thus, integrating LLMs and tools into tool learning agents has become a new emerging research direction. To this end, we present a systematic investigation and comprehensive review of tool-learning agents in this paper. We start by introducing the definition of the tool learning task for Agents and then illustrating the typical architecture of the tool-learning models. Since these tools are all defined by users, LLM does not know what tools there are and what their functions are. Thus, LLMs should first find appropriate tools and split the tool retrieval methods into two categories: training-based and non-training-based. To accurately complete the user task, it is important to decompose the task into several sub-tasks and execute them in the correct order. Following that, we introduce the tool planning methods and organize these works by whether they rely on the model’s inherent reasoning capabilities for planning or utilize external reasoning tools. Due to the rapid development of this field, we also introduce an emerging frontier direction: using multimodal tools for LLM. In addition, we compile current open-source benchmarks and evaluation metrics, focusing on their scale, composition, calculation methods, and assessment dimensions. Next, we introduce several application scenarios for the LLM-based tool learning methods. Finally, we discuss the safety and ethical issues involved in tool learning.

Abstract Graph stream is the model used to represent evolving graph data over time, which can be represented as a sequence of edge streams containing temporal information. To effectively manage an ultra large scale graph stream, existing designs usually use summarization structures based on compressed matrices to support approximate storage and querying of graph streams. However, the state-of-the-art structures are based on limited-sized compressed matrix. When dealing with dynamical graph stream data, they either use an extra adjacency list outside the compressed matrix to store left-over edges whose expected buckets in the matrix have been occupied by other previously inserted edges, or allocate new building blocks of compressed matrices to provide more space capacity. Such designs suffer from linear lookup time caused by the adjacency list or long system blocking time caused by data movement during structure scaling. Moreover, in graph stream applications with dynamically growing data sizes, recent data commonly carries greater significance and value. Existing designs fail to store the time information of items of graph streams in a space efficient way and leave recent data management over graph streams an unsolved problem. To address the dynamically expanding graph stream with the ability to accentuate the importance of recent data, in this work, we propose Sliding-ITeM, a novel adaptive-size graph stream summarization structure with a sliding window model. Two factors contribute to the efficiency of Sliding-ITeM. First, Sliding-ITeM proposes a novel fingerprint suffix index tree (FSIT) structure to efficiently manage the items assigned to a same bucket of a compressed matrix in a fine-grained and scalable way. It thus achieves time and space efficiency for graph stream management as well as avoiding costly blocking time for structure extending. Second, Sliding-ITeM divides continuous time into discrete time slices and stores items belong to different time slices in separate ITeM compressed matrices. Sliding-ITeM organizes the compressed matrices into a chain style chronologically and achieves efficient obtaining of value from recent data as well as removal of expired data following a sliding-window model. We conduct comprehensive experiments over large-scale graph stream data collected from real world systems to evaluate the performance of Sliding-ITeM. Experimental results show that it significantly reduces the operation latency by more than 67% in sliding window queries compared to state-of-the-art designs, while greatly reducing the system blocking duration by three orders of magnitude.

Abstract In this era of big data, seamless distribution of healthcare information is crucial for improving patient care and advancing medical research, necessitating meticulous attention to preserving health data privacy. However, overly stringent protection measures can impede the efficient utilization of invaluable resources for medical research and personalized healthcare, posing a central challenge in balancing privacy protection with effective data utilization. This study aims to explore various methods used to protect the privacy of patients’ health records, and evaluates their advantages and limitations. Additionally, it conducts an in-depth analysis of a public medical dataset concerning privacy protection, assessing the effectiveness of k-anonymity and l-diversity privacy criteria and examining the influence of quasi-identifier (QID) attributes on privacy preservation. The study showcases techniques to achieve privacy standards, including generalization and suppression. Furthermore, it introduces a novel approach that utilizes the genetic algorithm (GA) and a non-dominated sorting technique to maximize both privacy and utility in health data through multi-objective optimization. After examining the results, this paper offers a guide for data owners on selecting attributes for medical data publication and choosing suitable privacy preservation strategies. Through the exploration of the GA and the non-dominated sorting approach, this paper suggests that the proposed GA can offer promising non-dominated solutions to the issue of health data privacy in the era of data-driven healthcare. A combination of these algorithms can enhance privacy protection and provide healthcare professionals and researchers with essential knowledge, ultimately benefiting patient care and ensuring a more secure database system.

Relation extraction is a research hot-spot in the field of natural language processing, and aims at structured knowledge acquirement. However, existing methods still grapple with the issue of entity overlapping, where they treat relation types as inconsequential labels, overlooking the fact that relation type has a great influence on entity type hindering the performance of these models from further improving. Furthermore, current models are inadequate in handling the fine-grained aspect of entity positioning, which leads to ambiguity in entity boundary localization and uncertainty in relation inference, directly. In response to this challenge, a relation extraction model is proposed, which is guided by relational semantic cues and focused on entity boundary localization. The model uses an attention mechanism to align relation semantics with sentence information, so as to obtain the most relevant semantic expression to the target relation instance. It then incorporates an entity locator to harness additional positional features, thereby, enhancing the capability of the model to pinpoint entity start and end tags. Consequently, this approach effectively alleviates the problem of entity overlapping. Extensive experiments are conducted on the widely used datasets NYT and WebNLG. The experimental results show that the proposed model outperforms the baseline ones in F1 scores of the two datasets, and the improvement margin is up to 5.50% and 2.80%, respectively.

In recent years, the transformative evolution of cloud computing has reshaped organizational practices by enabling the outsourcing of web service applications. This shift has led to the emergence of the cloud environment, characterized by the involvement of Cloud Service Providers (CSPs) and intelligent applications. Cloud Service Composition (CSC) has become pivotal in this context, playing a crucial role in enhancing efficiency, Quality of Service (QoS), and customer satisfaction through the aggregation of diverse Cloud Services (CSs) to create composite services. However, the vast array of available CSs presents a challenge in efficiently addressing specified QoS requirements, turning CSC into a recognized NP-hard problem. Existing solutions, often involving third-party brokers, struggle with scalability in large-scale systems and overlook crucial security concerns. To address these limitations, we propose the Hierarchical Service Composition (HSC) approach, leveraging blockchain and federated learning to minimize computational complexity. The integration of Blockchain-enabled Federated Learning (BFL) facilitates machine learning model training with decentralized data, ensuring practicality and fairness. HSC comprises an initialization phase and two selection layers. The first selection layer enables each CSP to efficiently select services using a pre-trained model, while the second selection layer employs a blockchain-based QoS-aware mechanism for the final composition result, addressing privacy concerns. HSC introduces a novel framework, collaborative service selection methods, and a smart selection algorithm, demonstrating remarkable composition efficiency in extensive simulations compared to the baseline approach.

Anomaly detection on attributed graphs is a crucial topic for practical applications. Existing methods suffer from semantic mixture and imbalance issue because they commonly optimize the model based on the loss function for anomaly discrimination, mainly focusing on anomaly discrimination and ignoring representation learning. Graph Neural networks based techniques usually tend to map adjacent nodes into close semantic space. However, anomalous nodes commonly connect with numerous normal nodes directly, conflicting with the assortativity assumption. Additionally, there are far fewer anomalous nodes than normal nodes, leading to the imbalance problem. To address these challenges, a unique algorithm, decoupled self-supervised learning for anomaly detection (DSLAD), is proposed in this paper. DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection. DSLAD employs bilinear pooling and masked autoencoder as the anomaly discriminators. By decoupling anomaly discrimination and representation learning, a balanced feature space is constructed, in which nodes are more semantically discriminative, as well as imbalance issue can be resolved. Experiments conducted on various six benchmark datasets reveal the effectiveness of DSLAD.