Olaf Wolkenhauer

As machine learning becomes increasingly important in areas that handle sensitive data, preserving data privacy is crucial. We present a comprehensive systematic literature review of privacy-preserving deep learning applications. We categorize research papers in this field from 2017 to May 2024, distinguishing between inference and training, and considering single and multiple data owners. Our taxonomy offers a structured approach to understanding state-of-the-art methods and their suitability for various applications. We further provide real-world examples of each scenario to illustrate their practical relevance and discuss challenges and limitations. In addition to reviewing the existing research literature on privacy-preserving deep learning, we identify gaps in current knowledge and suggest future research directions. Our findings show that execution times are steadily decreasing, making privacy-preserving deep learning increasingly practical. Defending models against privacy attacks still poses challenges and often leads to decreased utility, e.g., in terms of accuracy, one of many trade-offs discussed in this paper. By systematizing a vast body of existing work and providing practical guidelines for technique selection and deployment, our paper serves as a valuable resource for experts, practitioners, and newcomers alike, facilitating cross-disciplinary collaboration and advancements in privacy-preserving deep learning.

Over the past years, embedding learning on networks has shown tremendous results in link prediction tasks for complex systems, with a wide range of real-life applications. Learning a representation for each node in a knowledge graph allows us to capture topological and semantic information, which can be processed in downstream analyses later. In the link prediction task, high-dimensional network information is encoded into low-dimensional vectors, which are then fed to a predictor to infer new connections between nodes in the network. As the network complexity (that is, the numbers of connections and types of interactions) grows, embedding learning turns out increasingly challenging. This review covers published models on embedding learning on multiplex networks for link prediction. First, we propose refined taxonomies to classify and compare 38 models (in 36 papers) across five methodological categories and three embedding classes. Second, we review and address the problem of reproducible and fair evaluation of embedding learning on multiplex networks for the link prediction task. Finally, we highlight challenges specific to performance evaluation on directed multiplex networks, and address them by introducing a novel and fair testing procedure. This review constitutes a crucial step towards the development of more performant and tractable embedding learning approaches for multiplex networks and their fair evaluation for the link prediction task. We also suggest guidelines on the evaluation of models, and provide an informed perspective on the challenges and tools currently available to address downstream analyses applied to multiplex networks.

Over the past years, embedding learning on networks has shown tremendous results in link prediction tasks for complex systems, with a wide range of real-life applications. Learning a representation for each node in a knowledge graph allows us to capture topological and semantic information, which can be processed in downstream analyses later. In the link prediction task, high-dimensional network information is encoded into low-dimensional vectors, which are then fed to a predictor to infer new connections between nodes in the network. As the network complexity (that is, the numbers of connections and types of interactions) grows, embedding learning turns out increasingly challenging. This review covers published models on embedding learning on multiplex networks for link prediction. First, we propose refined taxonomies to classify and compare models, depending on the type of embeddings and embedding techniques. Second, we review and address the problem of reproducible and fair evaluation of embedding learning on multiplex networks for the link prediction task. Finally, we tackle evaluation on directed multiplex networks by proposing a novel and fair testing procedure. This review constitutes a crucial step towards the development of more performant and tractable embedding learning approaches for multiplex networks and their fair evaluation for the link prediction task. We also suggest guidelines on the evaluation of models, and provide an informed perspective on the challenges and tools currently available to address downstream analyses applied to multiplex networks.

Over the past years, embedding learning on networks has shown tremendous results in link prediction tasks for complex systems, with a wide range of real-life applications. Learning a representation for each node in a knowledge graph allows us to capture topological and semantic information, which can be processed in downstream analyses later. In the link prediction task, high-dimensional network information is encoded into low-dimensional vectors, which are then fed to a predictor to infer new connections between nodes in the network. As the network complexity (that is, the numbers of connections and types of interactions) grows, embedding learning turns out increasingly challenging. This review covers published models on embedding learning on multiplex networks for link prediction. First, we propose refined taxonomies to classify and compare models, depending on the type of embeddings and embedding techniques. Second, we review and address the problem of reproducible and fair evaluation of embedding learning on multiplex networks for the link prediction task. Finally, we tackle evaluation on directed multiplex networks by proposing a novel and fair testing procedure. This review constitutes a crucial step towards the development of more performant and tractable embedding learning approaches for multiplex networks and their fair evaluation for the link prediction task. We also suggest guidelines on the evaluation of models, and provide an informed perspective on the challenges and tools currently available to address downstream analyses applied to multiplex networks.

Following the standard Eye Movement Desensitization and Reprocessing (EMDR) procedure, counting a fixed number of bilateral stimuli (BLS) is the guideline-congruent strategy for determining the length of the first stimulation set during the processing of pathogenic memories. For the subsequent sets, an individually adapted stimulation length depending on minimal nonverbal changes (MNCs) is recommended, such as changes in facial expression, muscle tone, posture, or breathing, which are assumed to reflect shifts in emotional valence. This exploratory survey study is the first work to investigate the relevance of these MNCs in clinical practice. This exploratory survey study examined how certified EMDR therapists apply the BLS procedure in practice and how they evaluate the relevance of MNCs. Eighty-eight certified EMDR therapists reported on their individual application of BLS. In addition, the perceived frequency, indicator value, and emotional valence of a broad range of MNCs were assessed. The results revealed substantial variability in therapists’ application of the BLS procedure. Whereas one quarter of therapists reported using counting as their preferred interruption strategy, approximately three quarters relied on MNCs. Nearly all therapists (98.2%) considered MNCs clinically important. Forehead relaxation, smiling, and respiratory changes were rated as particularly relevant indicators of valence change. Exploratory analyses suggested that therapist gender, therapeutic orientation, and patient clientele may be associated with variation in interruption strategies. These findings provide initial descriptive evidence of substantial heterogeneity in how EMDR therapists determine the length of BLS sets in clinical practice. They also identify specific MNCs that may be relevant targets for future observational and experimental research.