arXiv subjects

Anna Fensel

Publications and source records attributed to Anna Fensel.

7 recordsLinked to original sources

arXiv2025

A SHACL-based Data Consistency Solution for Contract Compliance Verification (Extended Paper)

In recent years, there have been many developments for GDPR-compliant data access and sharing based on consent. For more complex data sharing scenarios, where consent might not be sufficient, many parties rely on contracts. Before a contract is signed, it must undergo the process of contract negotiation within the contract lifecycle, which consists of negotiating the obligations associated with the contract. Contract compliance verification (CCV) provides a means to verify whether a contract is GDPR-compliant, i.e., adheres to legal obligations and there are no violations. The rise of knowledge graph (KG) adoption, enabling semantic interoperability using well-defined semantics, allows CCV to be applied on KGs. In the scenario of different participants negotiating obligations, there is a need for data consistency to ensure that CCV is done correctly. Recent work introduced the automated contracting tool (ACT), a KG-based and ODRL-employing tool for GDPR CCV, which was developed in the Horizon 2020 project smashHit (https://smashhit.eu). Although the tool reports violations with respect to obligations, it had limitations in verifying and ensuring compliance, as it did not use an interoperable semantic formalism, such as SHACL, and did not support users in resolving data inconsistencies. In this work, we propose a novel approach to overcome these limitations of ACT. We semi-automatically resolve CCV inconsistencies by providing repair strategies, which automatically propose (optimal) solutions to the user to re-establish data consistency and thereby support them in managing GDPR-compliant contract lifecycle data. We have implemented the approach, integrated it into ACT and tested its correctness and performance against basic CCV consistency requirements.

cs.LO↗

arXiv2022

Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding

We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseudo-labels, we use confidence thresholding for bounding boxes and mask scoring for masks. The approach has been tested with CenterMask, a single-stage anchor-free detector. Tested on the COCO 2017 val dataset, our architecture significantly (approx. +8 pp. in mask AP) outperforms the baseline at different supervision regimes. To the best of our knowledge, this is one of the first works tackling the problem of semi-supervised instance segmentation and the first one devoted to an anchor-free detector.

cs.CV↗

arXiv2022

KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles

We propose KGTN-ens, a framework extending the recent Knowledge Graph Transfer Network (KGTN) in order to incorporate multiple knowledge graph embeddings at a small cost. We evaluate it with different combinations of embeddings in a few-shot image classification task. We also construct a new knowledge source - Wikidata embeddings - and evaluate it with KGTN and KGTN-ens. Our approach outperforms KGTN in terms of the top-5 accuracy on the ImageNet-FS dataset for the majority of tested settings.

cs.CV↗

arXiv2021

Towards Knowledge Graphs Validation through Weighted Knowledge Sources

The performance of applications, such as personal assistants and search engines, relies on high-quality knowledge bases, a.k.a. Knowledge Graphs (KGs). To ensure their quality one important task is knowledge validation, which measures the degree to which statements or triples of KGs are semantically correct. KGs inevitably contain incorrect and incomplete statements, which may hinder their adoption in business applications as they are not trustworthy. In this paper, we propose and implement a Validator that computes a confidence score for every triple and instance in KGs. The computed score is based on finding the same instances across different weighted knowledge sources and comparing their features. We evaluate our approach by comparing its results against a baseline validation. Our results suggest that we can validate KGs with an f-measure of at least 75%. Time-wise, the Validator, performed a validation of 2530 instances in 15 minutes approximately. Furthermore, we give insights and directions toward a better architecture to tackle KG validation.

cs.DB↗

arXiv2018

The societal impact of big data: A research roadmap for Europe

With its rapid growth and increasing adoption, big data is producing a substantial impact in society. Its usage is opening both opportunities such as new business models and economic gains and risks such as privacy violations and discrimination. Europe is in need of a comprehensive strategy to optimise the use of data for a societal benefit and increase the innovation and competitiveness of its productive activities. In this paper, we contribute to the definition of this strategy with a research roadmap to capture the economic, social and ethical, legal and political benefits associated with the use of big data in Europe. The present roadmap considers the positive and negative externalities associated with big data, maps research and innovation topics in the areas of data management, processing, analytics, protection, visualisation, as well as non-technical topics, to the externalities they can tackle, and provides a time frame to address these topics in order to deliver social impact, skills development and standardisation. Finally, it also identifies what sectors will be most benefited by each of the research efforts. The goal of the roadmap is to guide European research efforts to develop a socially responsible big data economy, and to allow stakeholders to identify and meet big data challenges and proceed with a shared understanding of the societal impact, positive and negative externalities and concrete problems worth investigating in future programmes.

cs.CY↗

arXiv2017

A European research roadmap for optimizing societal impact of big data on environment and energy efficiency

We present a roadmap to guide European research efforts towards a socially responsible big data economy that maximizes the positive impact of big data in environment and energy efficiency. The goal of the roadmap is to allow stakeholders and the big data community to identify and meet big data challenges, and to proceed with a shared understanding of the societal impact, positive and negative externalities, and concrete problems worth investigating. It builds upon a case study focused on the impact of big data practices in the context of Earth Observation that reveals both positive and negative effects in the areas of economy, society and ethics, legal frameworks and political issues. The roadmap identifies European technical and non-technical priorities in research and innovation to be addressed in the upcoming five years in order to deliver societal impact, develop skills and contribute to standardization.

cs.CY↗

arXiv2017

Data Aggregation, Fusion and Recommendations for Strengthening Citizens Energy-aware Behavioural Profiles

In this paper, ENTROPY platform, an IT ecosystem for supporting energy efficiency in buildings through behavioural change of the occupants is provided. The ENTROPY platform targets at providing a set of mechanisms for accelerating the adoption of energy efficient practices through the increase of the energy awareness and energy saving potential of the occupants. The platform takes advantage of novel sensor networking technologies for supporting efficient sensor data aggregation mechanisms, semantic web technologies for unified data representation, machine learning mechanisms for getting insights from the available data and recommendation mechanisms for providing personalised content to end users. These technologies are combined and provided through an integrated platform, targeting at leading to occupants' behavioural change with regards to their energy consumption profiles.

cs.CY↗