The use and creation of machine‐learning‐based solutions to solve problems or reduce
their computational costs are becoming increasingly widespread in many domains. Deep …

Real-world problems often exhibit complex relationships and dependencies, which can be
effectively captured by graph learning systems. Graph attention networks (GATs) have …

Whether AI explanations can help users achieve specific tasks efficiently (ie, usable
explanations) is significantly influenced by their visual presentation. While many techniques …

The past decade has witnessed a plethora of works that leverage the power of visualization
(VIS) to interpret machine learning (ML) models. The corresponding research topic, VIS4ML …

Recently, large pretrained language models have achieved compelling performance on
commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the …

The increasing reliance on Large Language Models (LLMs) for health information seeking
can pose severe risks due to the potential for misinformation and the complexity of these …

Several areas in science and engineering have the relationships between their underlying
data which can be represented as graphs, for example, molecular chemistry, node …

In this work, we propose an interactive visual approach for the exploration and formation of
structural relationships in embeddings of high-dimensional data. These structural …

Graph neural networks (GNNs) are a class of powerful machine learning tools that model
node relations for making predictions of nodes or links. GNN developers rely on quantitative …

Benchmark datasets play an important role in evaluating Natural Language Understanding
(NLU) models. However, shortcuts—unwanted biases in the benchmark datasets—can …