A Review of the Role of Causality in Developing Trustworthy AI Systems

Ganguly, Niloy; Fazlija, Dren; Badar, Maryam; Fisichella, Marco; Sikdar, Sandipan; Schrader, Johanna; Wallat, Jonas; Rudra, Koustav; Koubarakis, Manolis; Patro, Gourab K; Amri, Wadhah Zai El; Nejdl, Wolfgang

doi:10.48550/arxiv.2302.06975

Cited by 2 publications

(4 citation statements)

References 186 publications

(361 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In diverse applications, neurosymbolic AI and GNNs play a crucial role. In drug discovery, they combine expert knowledge with GNN-driven insights to accelerate the identification of potential drug candidates [27]. In healthcare, these models enhance the interpretability of medical decision-making by providing explanations for diagnoses through the integration of symbolic medical knowledge with learned patterns from patient data [28].…”

Section: Neurosymbolic Ai and Gnnsmentioning

confidence: 99%

Evaluating Ontology-Based PD Monitoring and Alerting in Personal Health Knowledge Graphs and Graph Neural Networks

Zafeiropoulos,

Bitilis,

Tsekouras

et al. 2024

Information

View full text Add to dashboard Cite

In the realm of Parkinson’s Disease (PD) research, the integration of wearable sensor data with personal health records (PHR) has emerged as a pivotal avenue for patient alerting and monitoring. This study delves into the complex domain of PD patient care, with a specific emphasis on harnessing the potential of wearable sensors to capture, represent and semantically analyze crucial movement data and knowledge. The primary objective is to enhance the assessment of PD patients by establishing a robust foundation for personalized health insights through the development of Personal Health Knowledge Graphs (PHKGs) and the employment of personal health Graph Neural Networks (PHGNNs) that utilize PHKGs. The objective is to formalize the representation of related integrated data, unified sensor and PHR data in higher levels of abstraction, i.e., in a PHKG, to facilitate interoperability and support rule-based high-level event recognition such as patient’s missing dose or falling. This paper, extending our previous related work, presents the Wear4PDmove ontology in detail and evaluates the ontology within the development of an experimental PHKG. Furthermore, this paper focuses on the integration and evaluation of PHKG within the implementation of a Graph Neural Network (GNN). This work emphasizes the importance of integrating PD-related data for monitoring and alerting patients with appropriate notifications. These notifications offer health experts precise and timely information for the continuous evaluation of personal health-related events, ultimately contributing to enhanced patient care and well-informed medical decision-making. Finally, the paper concludes by proposing a novel approach for integrating personal health KGs and GNNs for PD monitoring and alerting solutions.

show abstract

Section: Neurosymbolic Ai and Gnnsmentioning

confidence: 99%

Evaluating Ontology-Based PD Monitoring and Alerting in Personal Health Knowledge Graphs and Graph Neural Networks

Zafeiropoulos,

Bitilis,

Tsekouras

et al. 2024

Information

View full text Add to dashboard Cite

show abstract

“…Posthoc Suitable to explain an already deployed model [11][12][13][14]23,32,33,[48][49][50] Antehoc Suitable when an application specifies the need to build models that have interpretability built into its design [15][16][17]22,38,[51][52][53][54] Explanation Scope…”

Section: Incorporation Stagementioning

confidence: 99%

“…Many such cause-effect relationships exist in nature. It is of interest to the research community to see if the machine learning models capture such causal relationships [11][12][13][14] and design models which work based on causal relationships so that the spurious correlations [34] are not picked up to arrive at the prediction [15][16][17].…”

Section: Causal Explanationsmentioning

confidence: 99%

“…Explaining image classifiers based on causal relationships poses a challenge due to the limited knowledge of the underlying causal structure between image features. Some approaches [11][12][13][14] aim to extract the causal relationships exhibited by model representations and compare them with available proxy domain knowledge in a posthoc manner, without disrupting the black box classifier being explained. Another category of approaches [15][16][17] enforces the classifiers to adhere to the existing causal relationships, similar to the antehoc or explainability-by-design approaches, in order to make predictions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Image Classification: The Journey So Far and the Road Ahead

Kamakshi,

Krishnan

2023

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address the interpretability challenges posed by complex machine learning models. In this survey paper, we provide a comprehensive analysis of existing approaches in the field of XAI, focusing on the tradeoff between model accuracy and interpretability. Motivated by the need to address this tradeoff, we conduct an extensive review of the literature, presenting a multi-view taxonomy that offers a new perspective on XAI methodologies. We analyze various sub-categories of XAI methods, considering their strengths, weaknesses, and practical challenges. Moreover, we explore causal relationships in model explanations and discuss approaches dedicated to explaining cross-domain classifiers. The latter is particularly important in scenarios where training and test data are sampled from different distributions. Drawing insights from our analysis, we propose future research directions, including exploring explainable allied learning paradigms, developing evaluation metrics for both traditionally trained and allied learning-based classifiers, and applying neural architectural search techniques to minimize the accuracy–interpretability tradeoff. This survey paper provides a comprehensive overview of the state-of-the-art in XAI, serving as a valuable resource for researchers and practitioners interested in understanding and advancing the field.

show abstract

A Review of the Role of Causality in Developing Trustworthy AI Systems

Cited by 2 publications

References 186 publications

Evaluating Ontology-Based PD Monitoring and Alerting in Personal Health Knowledge Graphs and Graph Neural Networks

Evaluating Ontology-Based PD Monitoring and Alerting in Personal Health Knowledge Graphs and Graph Neural Networks

Explainable Image Classification: The Journey So Far and the Road Ahead

Contact Info

Product

Resources

About