Explainable AI (XAI) has become an increasingly important topic for understanding and attributing the predictions made by complex Time Series Classification (TSC) models. Among attribution methods, SHapley Additive exPlanations (SHAP) is widely regarded as an excellent attribution method, but its computational complexity, which scales exponentially with the number of features, limits its practicality for long time series. To address this, recent studies have shown that aggregating features via segmentation, to compute a single attribution value for a group of consecutive time points, drastically reduces SHAP running time. However, the choice of the optimal segmentation strategy remains an open question. In this work, we investigated eight different Time Series Segmentation algorithms to understand how segment compositions affect the explanation quality. We evaluate these approaches using two established XAI evaluation methodologies: InterpretTime and AUC Difference. Through experiments on both Multivariate (MTS) and Univariate Time Series (UTS), we find that the number of segments has a greater impact on explanation quality than the specific segmentation method. Notably, equal-length segmentation consistently outperforms most of the custom time series segmentation algorithms. Furthermore, we introduce a novel attribution normalisation technique that weights segments by their length and we show that it consistently improves attribution quality.

Many researchers have suggested that local post-hoc explanation algorithms can be used to gain insights into the behavior of complex machine learning models. However, theoretical guarantees about such algorithms only exist for simple decision functions, and it is unclear whether and under which assumptions similar results might exist for complex models. In this paper, we introduce a general, learning-theory-based framework for what it means for an explanation to provide information about a decision function. We call an explanation informative if it serves to reduce the complexity of the space of plausible decision functions. With this approach, we show that many popular explanation algorithms are not informative when applied to complex decision functions, providing a rigorous mathematical rejection of the idea that it should be possible to explain any model. We then derive conditions under which different explanation algorithms become informative. These are often stronger than what one might expect. For example, gradient explanations and counterfactual explanations are non-informative with respect to the space of differentiable functions, and SHAP and anchor explanations are not informative with respect to the space of decision trees. Based on these results, we discuss how explanation algorithms can be modified to become informative. While the proposed analysis of explanation algorithms is mathematical, we argue that it holds strong implications for the practical applicability of these algorithms, particularly for auditing, regulation, and high-risk applications of AI.

Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven to be NP-Hard in various configurations. Recent works have unveiled positive complexity results regarding the computation of the SHAP score for specific model families, encompassing decision trees, random forests, and some classes of boolean circuits. Yet, all these positive results hinge on the assumption of feature independence, often simplistic in real-world scenarios. In this article, we investigate the computational complexity of the SHAP score by relaxing this assumption and introducing a Markovian perspective. We show that, under the Markovian assumption, computing the SHAP score for the class of Weighted automata, Disjoint DNFs and Decision Trees can be performed in polynomial time, offering a first positive complexity result for the problem of SHAP score computation that transcends the limitations of the feature independence assumption.

The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented.

Nowadays, the interpretation of why a machine learning (ML) model makes certain inferences is as crucial as the accuracy of such inferences. Some ML models like the decision tree possess inherent interpretability that can be directly comprehended by humans. Others like artificial neural networks (ANN), however, rely on external methods to uncover the deduction mechanism. SHapley Additive exPlanations (SHAP) is one of such external methods, which requires a background dataset when interpreting ANNs. Generally, a background dataset consists of instances randomly sampled from the training dataset. However, the sampling size and its effect on SHAP remain to be unexplored. In our empirical study on the MIMIC-III dataset, we show that the two core explanations - SHAP values and variable rankings fluctuate when using different background datasets acquired from random sampling, indicating that users cannot unquestioningly trust the one-shot interpretation from SHAP. Luckily, such fluctuation decreases with the increase of the background dataset size. Also, we notice an U-shape in the stability assessment of SHAP variable rankings, demonstrating that SHAP is more reliable in ranking the most and least important variables compared to moderately important ones. Overall, our results suggest that users should take into account how background data affects SHAP results, with improved SHAP stability as the background sample size increases.

Recent development in the field of explainable artificial intelligence (XAI) has helped improve trust in Machine-Learning-as-a-Service (MLaaS) systems, in which an explanation is provided together with the model prediction in response to each query. However, XAI also opens a door for adversaries to gain insights into the black-box models in MLaaS, thereby making the models more vulnerable to several attacks. For example, feature-based explanations (e.g., SHAP) could expose the top important features that a black-box model focuses on. Such disclosure has been exploited to craft effective backdoor triggers against malware classifiers. To address this trade-off, we introduce a new concept of achieving local differential privacy (LDP) in the explanations, and from that we establish a defense, called XRand, against such attacks. We show that our mechanism restricts the information that the adversary can learn about the top important features, while maintaining the faithfulness of the explanations.

We conduct relatively extensive investigations of automatic hate speech (HS) detection using different state-of-the-art (SoTA) baselines over 11 subtasks of 6 different datasets. Our motivation is to determine which of the recent SoTA models is best for automatic hate speech detection and what advantage methods like data augmentation and ensemble may have on the best model, if any. We carry out 6 cross-task investigations. We achieve new SoTA on two subtasks - macro F1 scores of 91.73% and 53.21% for subtasks A and B of the HASOC 2020 dataset, where previous SoTA are 51.52% and 26.52%, respectively. We achieve near-SoTA on two others - macro F1 scores of 81.66% for subtask A of the OLID 2019 dataset and 82.54% for subtask A of the HASOC 2021 dataset, where SoTA are 82.9% and 83.05%, respectively. We perform error analysis and use two explainable artificial intelligence (XAI) algorithms (IG and SHAP) to reveal how two of the models (Bi-LSTM and T5) make the predictions they do by using examples. Other contributions of this work are 1) the introduction of a simple, novel mechanism for correcting out-of-class (OOC) predictions in T5, 2) a detailed description of the data augmentation methods, 3) the revelation of the poor data annotations in the HASOC 2021 dataset by using several examples and XAI (buttressing the need for better quality control), and 4) the public release of our model checkpoints and codes to foster transparency.

Shap explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent interest from both academia and industry, it is not known whether Shap explanations of common machine learning models can be computed efficiently. In this paper, we establish the complexity of computing the Shap explanation in three important settings. First, we consider fully-factorized data distributions, and show that the complexity of computing the Shap explanation is the same as the complexity of computing the expected value of the model. This fully-factorized setting is often used to simplify the Shap computation, yet our results show that the computation can be intractable for commonly used models such as logistic regression. Going beyond fully-factorized distributions, we show that computing Shap explanations is already intractable for a very simple setting: computing Shap explanations of trivial classifiers over naive Bayes distributions. Finally, we show that even computing Shap over the empirical distribution is #P-hard.