Explainable AI (XAI) refers to the design and development of artificial intelligence systems in a way that allows humans to understand and interpret their decisions and actions. The goal of XAI is to make AI systems more transparent and accountable by providing insights into how they arrive at specific outcomes. This is particularly important in critical applications where trust, accountability, and understanding the decision-making process are essential. Explainability in AI can be achieved through various methods, including transparent model architectures, feature importance analysis, and generating human-readable explanations for model predictions.


Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks

Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured data, and their expansive application in sensitive domains requires a comprehensive understanding of their decision-making processes — necessitating a framework for GNN explainability. An explanation function for GNNs takes a pre-trained GNN along with a graph as input, to produce a ‘sufficient statistic’ subgraph with respect to the graph label. A main challenge in studying GNN explainability is to provide f idelity measures that evaluate the performance of these explanation functions. This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics, including Fid+, Fid?, and Fid?. Specifically, a formal, information-theoretic definition of explainability is introduced and it is shown that existing metrics often fail to align with this definition across various statistical scenarios. The reason is due to potential distribution shifts when subgraphs are removed in computing these fidelity measures. Subsequently, a robust class of fidelity measures are introduced, and it is shown analytically that they are resilient to distribution shift issues and are applicable in a wide range of scenarios. Extensive empirical analysis on both synthetic and real datasets are provided to illustrate that the proposed metrics are more coherent with gold standard metrics. The source code is available at https://trustai4s-lab.github.io/fidelity.

Explainable Anomaly Detection System for Categorical Sensor Data in Internet of Things

Internet of things (IoT) applications deploy massive number of sensors to monitor the system and environment. Anomaly detection on streaming sensor data is an important task for IoT maintenance and operation. However, there are two major challenges for anomaly detection in real IoT applications: (1) many sensors report categorical values rather than numerical readings, (2) the end users may not understand the detection results, they require additional knowledge and explanations to make decision and take action. Unfortunately, most existing solutions cannot satisfy such requirements. To bridge the gap, we design and develop an eXplainable Anomaly Detection System (XADS) for categorical sensor data. XADS trains models from historical normal data and conducts online monitoring. XADS detects the anomalies in an explainable way: the system not only reports anomalies’ time periods, types, and detailed information, but also provides explanations on why they are abnormal, and what the normal data look like. Such information significantly helps the decision making for users. Moreover, XADS requires limited parameter setting in advance, yields high accuracy on detection results and comes with a user-friendly interface, making it an efficient and effective tool to monitor a wide variety of IoT applications.