GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction.

Graph Anomaly Detection (GAD) is a technique used to identify abnormal nodes within graphs, finding applications in network security, fraud detection, social media spam detection, and various other domains. A common method for GAD is Graph Auto-Encoders (GAEs), which encode graph data into node representations and identify anomalies by assessing the reconstruction quality of the graphs based on these representations. However, existing GAE models are primarily optimized for direct link reconstruction, resulting in nodes connected in the graph being clustered in the latent space.

Reaching Distance Influences Perceptual Decisions.

Decision making is an integral part of everyday life. Recently, there has been a growing interest in the potential influence of action on perceptual decisions, following ideas of embodied decision making. Studies examining decisions regarding the direction of noisy visual motion have found a bias towards the least effortful response option in experiments in which the differences in motor costs associated with alternative response actions were implicit, but not in an experiment in which these differences were made explicit.

The influence of body orientation on length judgements.

Perceiving the size of a visual object requires the combination of various sources of visual information. A recent paper by Kim et al. (Body Orientation Affects the Perceived Size of Objects.

Seeking under threat of adversity: assessing control over reward pursuit in rats.

Rationale: Substance use disorder (SUD) is a chronic relapsing brain disorder that is characterised by loss of control over substance use. A variety of rodent models employing punishment setups have been developed to assess loss of control over substance use, i.e.

A Circle-Drawing Task for Studying Reward-Based Motor Learning in Children and Adults.

Childhood is an obvious period for motor learning, since children's musculoskeletal and nervous systems are still in development. Adults adapt movements based on reward feedback about success and failure, but it is less established whether school-age children also exhibit such reward-based motor learning. We designed a new 'circle-drawing' task suitable for assessing reward-based motor learning in both children (7-17 years old) and adults (18-65 years old).