Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI

Holzinger, Andreas; Malle, Bernd; Saranti, Anna; Pfeifer, Bastian

doi:10.1016/j.inffus.2021.01.008

Cited by 268 publications

(126 citation statements)

References 39 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…As stated in [55], explainable methods are becoming more relevant, particularly in the health-care domain. Thus, it is necessary to consider many aspects when designing explainable ML methods, e.g., who is the domain expert?, who are the affected users?, among others [56,57]. Accordingly, Table . 12 Attention mechanism visualization for the OMT classification task Motive Sample text (closest English translation) A (she needs understanding and turns to someone who listens to and understands her; she feels safe and accepted and tells what is burdensome; she is accepted as she is.)…”

Section: Results Analysismentioning

confidence: 93%

Applying Attention-Based Models for Detecting Cognitive Processes and Mental Health Conditions

Villatoro-Tello

Parida

Kumar³

et al. 2021

Cogn Comput

View full text Add to dashboard Cite

According to the psychological literature, implicit motives allow for the characterization of behavior, subsequent success, and long-term development. Contrary to personality traits, implicit motives are often deemed to be rather stable personality characteristics. Normally, implicit motives are obtained by Operant Motives, unconscious intrinsic desires measured by the Operant Motive Test (OMT). The OMT test requires participants to write freely descriptions associated with a set of provided images and questions. In this work, we explore different recent machine learning techniques and various text representation techniques for facing the problem of the OMT classification task. We focused on advanced language representations (e.g, BERT, XLM, and DistilBERT) and deep Supervised Autoencoders for solving the OMT task. We performed an exhaustive analysis and compared their performance against fully connected neural networks and traditional support vector classifiers. Our comparative study highlights the importance of BERT which outperforms the traditional machine learning techniques by a relative improvement of 7.9%. In addition, we performed an analysis of how the BERT attention mechanism is being modified. Our findings indicate that the writing style features acquire higher importance at the moment of accurately identifying the different OMT categories. This is the first time that a study to determine the performance of different transformer-based architectures in the OMT task is performed. Similarly, our work propose, for the first time, using deep supervised autoencoders in the OMT classification task. Our experiments demonstrate that transformer-based methods exhibit the best empirical results, obtaining a relative improvement of 7.9% over the competitive baseline suggested as part of the GermEval 2020 challenge. Additionally, we show that features associated with the writing style are more important than content-based words. Some of these findings show strong connections to previously reported behavioral research on the implicit psychometrics theory.

show abstract

Section: Results Analysismentioning

confidence: 93%

Applying Attention-Based Models for Detecting Cognitive Processes and Mental Health Conditions

Villatoro-Tello

Parida

Kumar³

et al. 2021

Cogn Comput

View full text Add to dashboard Cite

show abstract

“…Another way to improve interpretability is the use of graph-based models, as introduced in Section 4.5. As mentioned earlier, GNNs have advantages in multi-omics integrated analysis and intrinsically allow for more explainability [159]. Various recent studies are reporting the merit of graph-oriented models.…”

Section: Discussionmentioning

confidence: 99%

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

Park

Heider

Hauschild

2021

Cancers

View full text Add to dashboard Cite

The rapid improvement of next-generation sequencing (NGS) technologies and their application in large-scale cohorts in cancer research led to common challenges of big data. It opened a new research area incorporating systems biology and machine learning. As large-scale NGS data accumulated, sophisticated data analysis methods became indispensable. In addition, NGS data have been integrated with systems biology to build better predictive models to determine the characteristics of tumors and tumor subtypes. Therefore, various machine learning algorithms were introduced to identify underlying biological mechanisms. In this work, we review novel technologies developed for NGS data analysis, and we describe how these computational methodologies integrate systems biology and omics data. Subsequently, we discuss how deep neural networks outperform other approaches, the potential of graph neural networks (GNN) in systems biology, and the limitations in NGS biomedical research. To reflect on the various challenges and corresponding computational solutions, we will discuss the following three topics: (i) molecular characteristics, (ii) tumor heterogeneity, and (iii) drug discovery. We conclude that machine learning and network-based approaches can add valuable insights and build highly accurate models. However, a well-informed choice of learning algorithm and biological network information is crucial for the success of each specific research question.

show abstract

“…These very versatile approaches also work on graphbased data. 9 Other methods include deconvolution, which involves reversing the effects of convolution and generating from two functions a third function that is then the product of both, as well as guided backpropagation. 10 All of these methods constitute an excellent preprocessing step.…”

Section: Explainabilitymentioning

confidence: 99%

Toward Human–AI Interfaces to Support Explainability and Causability in Medical AI

Holzinger

Müller

2021

Computer

Self Cite

View full text Add to dashboard Cite

Our concept of causability is a measure of whether and to what extent humans can understand a given machine explanation.We motivate causability with a clinical case from cancer research.We argue for using causability in medical artificial intelligence (AI) to develop and evaluate future human-AI interfaces.A chieving human-level artificial intelligence (AI) has been the ambition since the emergence of this field. Because of the availability of big data and the necessary computing power, statistical machine learning, especially deep learning, has now made tremendous progress, even in domains as complex as medicine. For example, the work of the Stanford machine learning group on dermatology 1 was popularized in Europe as "AI is better than doctors." The group trained a deep learning model directly from dermatological images by using only pixels and disease labels as the inputs for the classification of skin lesions. For pretraining, they used 1.3 million images from the 2014 ImageNet challenge and then 130,000 clinical images with about 2,000 different diseases. The results, with an average classification performance of 92%, were on par with, or even better than, those of human dermatologists. This is a remarkable achievement, and there is no question that AI will become very important for medicine.Despite these impressive successes, we must be aware that these previous approaches rely on statistical model-free learning. Relying solely on statistical correlations can be very dangerous, especially in medicine, because correlation must not be confused with causality, which is completely missing in current AI. This is a general

show abstract

Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI

Cited by 268 publications

References 39 publications

Applying Attention-Based Models for Detecting Cognitive Processes and Mental Health Conditions

Applying Attention-Based Models for Detecting Cognitive Processes and Mental Health Conditions

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

Toward Human–AI Interfaces to Support Explainability and Causability in Medical AI

Contact Info

Product

Resources

About