Explainable artificial intelligence (XAI) methods lack ground truth. In its place, method developers have relied on axioms to determine desirable properties for their explanations' behavior. For high stakes uses of machine learning that require explainability, it is not sufficient to rely on axioms as the implementation, or its usage, can fail to live up to the ideal. As a result, there exists active research on validating the performance of XAI methods. The need for validation is especially magnified in domains with a reliance on XAI. A procedure frequently used to assess their utility, and to some extent their fidelity, is an ablation study. By perturbing the input variables in rank order of importance, the goal is to assess the sensitivity of the model's performance. Perturbing important variables should correlate with larger decreases in measures of model capability than perturbing less important features. While the intent is clear, the actual implementation details have not been studied rigorously for tabular data. Using five datasets, three XAI methods, four baselines, and three perturbations, we aim to show 1) how varying perturbations and adding simple guardrails can help to avoid potentially flawed conclusions, 2) how treatment of categorical variables is an important consideration in both post-hoc explainability and ablation studies, and 3) how to identify useful baselines for XAI methods and viable perturbations for ablation studies.
High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation. Many techniques have been developed to generate better saliency using neural networks. However, they are often limited to specific saliency visualisation methods or saliency issues. We propose a novel saliency enhancing approach called SESS (Saliency Enhancing with Scaling and Sliding). It is a method and model agnostic extension to existing saliency map generation methods. With SESS, existing saliency approaches become robust to scale variance, multiple occurrences of target objects, presence of distractors and generate less noisy and more discriminative saliency maps. SESS improves saliency by fusing saliency maps extracted from multiple patches at different scales from different areas, and combines these individual maps using a novel fusion scheme that incorporates channel-wise weights and spatial weighted average. To improve efficiency, we introduce a pre-filtering step that can exclude uninformative saliency maps to improve efficiency while still enhancing overall results. We evaluate SESS on object recognition and detection benchmarks where it achieves significant improvement. The code is released publicly to enable researchers to verify performance and further development. Code is available at: https://github.com/neouyghur/SESS
Tree Ensemble (TE) models, such as Gradient Boosted Trees, often achieve optimal performance on tabular datasets, yet their lack of transparency poses challenges for comprehending their decision logic. This paper introduces TE2Rules (Tree Ensemble to Rules), a novel approach for explaining binary classification tree ensemble models through a list of rules, particularly focusing on explaining the minority class. Many state-of-the-art explainers struggle with minority class explanations, making TE2Rules valuable in such cases. The rules generated by TE2Rules closely approximate the original model, ensuring high fidelity, providing an accurate and interpretable means to understand decision-making. Experimental results demonstrate that TE2Rules scales effectively to tree ensembles with hundreds of trees, achieving higher fidelity within runtimes comparable to baselines. TE2Rules allows for a trade-off between runtime and fidelity, enhancing its practical applicability. The implementation is available here: https://github.com/linkedin/TE2Rules.
Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these approaches and understand their inner workings mechanisms. Given that contrastive models are trained with interdependent and interacting inputs and aim to learn invariance through data augmentation, the existing methods for explaining single-image systems (e.g., image classification models) are inadequate as they fail to account for these factors and typically assume independent inputs. Additionally, there is a lack of evaluation metrics designed to assess pairs of explanations, and no analytical studies have been conducted to investigate the effectiveness of different techniques used to explaining contrastive learning. In this work, we design visual explanation methods that contribute towards understanding similarity learning tasks from pairs of images. We further adapt existing metrics, used to evaluate visual explanations of image classification systems, to suit pairs of explanations and evaluate our proposed methods with these metrics. Finally, we present a thorough analysis of visual explainability methods for contrastive learning, establish their correlation with downstream tasks and demonstrate the potential of our approaches to investigate their merits and drawbacks.
The rise of AI methods to make predictions and decisions has led to a pressing need for more explainable artificial intelligence (XAI) methods. One common approach for XAI is to produce a post-hoc explanation, explaining why a black box ML model made a certain prediction. Formal approaches to post-hoc explanations provide succinct reasons for why a prediction was made, as well as why not another prediction was made. But these approaches assume that features are independent and uniformly distributed. While this means that "why" explanations are correct, they may be longer than required. It also means the "why not" explanations may be suspect as the counterexamples they rely on may not be meaningful. In this paper, we show how one can apply background knowledge to give more succinct "why" formal explanations, that are presumably easier to interpret by humans, and give more accurate "why not" explanations. In addition, we show how to use existing rule induction techniques to efficiently extract background information from a dataset, and also how to report which background information was used to make an explanation, allowing a human to examine it if they doubt the correctness of the explanation.
The expected goal provides a more representative measure of the team and player performance which also suit the low-scoring nature of football instead of score in modern football. The score of a match involves randomness and often may not represent the performance of the teams and players, therefore it has been popular to use the alternative statistics in recent years such as shots on target, ball possessions, and drills. To measure the probability of a shot being a goal by the expected goal, several features are used to train an expected goal model which is based on the event and tracking football data. The selection of these features, the size and date of the data, and the model which are used as the parameters that may affect the performance of the model. Using black-box machine learning models for increasing the predictive performance of the model decreases its interpretability that causes the loss of information that can be gathered from the model. This paper proposes an accurate expected goal model trained consisting of 315,430 shots from seven seasons between 2014-15 and 2020-21 of the top-five European football leagues. Moreover, this model is explained by using explainable artificial intelligence tool to obtain an explainable expected goal model for evaluating a team or player performance. To the best of our knowledge, this is the first paper that demonstrates a practical application of an explainable artificial intelligence tool aggregated profiles to explain a group of observations on an accurate expected goal model for monitoring the team and player performance. Moreover, these methods can be generalized to other sports branches.
Insects are a crucial part of our ecosystem. Sadly, in the past few decades, their numbers have worryingly decreased. In an attempt to gain a better understanding of this process and monitor the insects populations, Deep Learning may offer viable solutions. However, given the breadth of their taxonomy and the typical hurdles of fine grained analysis, such as high intraclass variability compared to low interclass variability, insect classification remains a challenging task. There are few benchmark datasets, which impedes rapid development of better AI models. The annotation of rare species training data, however, requires expert knowledge. Explainable Artificial Intelligence (XAI) could assist biologists in these annotation tasks, but choosing the optimal XAI method is difficult. Our contribution to these research challenges is threefold: 1) a dataset of thoroughly annotated images of wild bees sampled from the iNaturalist database, 2) a ResNet model trained on the wild bee dataset achieving classification scores comparable to similar state-of-the-art models trained on other fine-grained datasets and 3) an investigation of XAI methods to support biologists in annotation tasks.
Today's most advanced machine-learning models are hardly scrutable. The key challenge for explainability methods is to help assisting researchers in opening up these black boxes, by revealing the strategy that led to a given decision, by characterizing their internal states or by studying the underlying data representation. To address this challenge, we have developed Xplique: a software library for explainability which includes representative explainability methods as well as associated evaluation metrics. It interfaces with one of the most popular learning libraries: Tensorflow as well as other libraries including PyTorch, scikit-learn and Theano. The code is licensed under the MIT license and is freely available at github.com/deel-ai/xplique.
The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying where important features occur (but not providing information about what they represent), global explanation techniques visualize what concepts a model has generally learned to encode. Both types of methods thus only provide partial insights and leave the burden of interpreting the model's reasoning to the user. In this work we introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives and thus allows answering both the "where" and "what" questions for individual predictions. We demonstrate the capability of our method in various settings, showcasing that CRP leads to more human interpretable explanations and provides deep insights into the model's representation and reasoning through concept atlases, concept composition analyses, and quantitative investigations of concept subspaces and their role in fine-grained decision making.
This study uses supervised machine learning (SML) and explainable artificial intelligence (AI) to model, predict and understand human decision-making during skillful joint-action. Long short-term memory networks were trained to predict the target selection decisions of expert and novice actors completing a dyadic herding task. Results revealed that the trained models were expertise specific and could not only accurately predict the target selection decisions of expert and novice herders but could do so at timescales that preceded an actor's conscious intent. To understand what differentiated the target selection decisions of expert and novice actors, we then employed the explainable-AI technique, SHapley Additive exPlanation, to identify the importance of informational features (variables) on model predictions. This analysis revealed that experts were more influenced by information about the state of their co-herders compared to novices. The utility of employing SML and explainable-AI techniques for investigating human decision-making is discussed.
Deep learning has become a one-size-fits-all solution for technical and business domains thanks to its flexibility and adaptability. It is implemented using opaque models, which unfortunately undermines the outcome trustworthiness. In order to have a better understanding of the behavior of a system, particularly one driven by time series, a look inside a deep learning model so-called posthoc eXplainable Artificial Intelligence (XAI) approaches, is important. There are two major types of XAI for time series data, namely model-agnostic and model-specific. Model-specific approach is considered in this work. While other approaches employ either Class Activation Mapping (CAM) or Attention Mechanism, we merge the two strategies into a single system, simply called the Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time Series (TSEM). TSEM combines the capabilities of RNN and CNN models in such a way that RNN hidden units are employed as attention weights for the CNN feature maps temporal axis. The result shows that TSEM outperforms XCM. It is similar to STAM in terms of accuracy, while also satisfying a number of interpretability criteria, including causality, fidelity, and spatiotemporality.
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. Evaluating such methods is challenging since no ground truth attributions exist. We thus propose three novel evaluation schemes to more reliably measure the faithfulness of those methods, to make comparisons between them more fair, and to make visual inspection more systematic. To address faithfulness, we propose a novel evaluation setting (DiFull) in which we carefully control which parts of the input can influence the output in order to distinguish possible from impossible attributions. To address fairness, we note that different methods are applied at different layers, which skews any comparison, and so evaluate all methods on the same layers (ML-Att) and discuss how this impacts their performance on quantitative metrics. For more systematic visualizations, we propose a scheme (AggAtt) to qualitatively evaluate the methods on complete datasets. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods. Finally, we propose a post-processing smoothing step that significantly improves the performance of some attribution methods, and discuss its applicability.
Counterfactual explanations (CFEs) highlight what changes to a model's input would have changed its prediction in a particular way. CFEs have gained considerable traction as a psychologically grounded solution for explainable artificial intelligence (XAI). Recent innovations introduce the notion of computational plausibility for automatically generated CFEs, enhancing their robustness by exclusively creating plausible explanations. However, practical benefits of such a constraint on user experience and behavior is yet unclear. In this study, we evaluate objective and subjective usability of computationally plausible CFEs in an iterative learning design targeting novice users. We rely on a novel, game-like experimental design, revolving around an abstract scenario. Our results show that novice users actually benefit less from receiving computationally plausible rather than closest CFEs that produce minimal changes leading to the desired outcome. Responses in a post-game survey reveal no differences in terms of subjective user experience between both groups. Following the view of psychological plausibility as comparative similarity, this may be explained by the fact that users in the closest condition experience their CFEs as more psychologically plausible than the computationally plausible counterpart. In sum, our work highlights a little-considered divergence of definitions of computational plausibility and psychological plausibility, critically confirming the need to incorporate human behavior, preferences and mental models already at the design stages of XAI approaches. In the interest of reproducible research, all source code, acquired user data, and evaluation scripts of the current study are available: https://github.com/ukuhl/PlausibleAlienZoo
There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of "attention as explanation" has so far been evaluated by computing the rank correlation between attention-based explanations and existing feature attribution explanations using LSTM-based models. In our work, we (i) compare the rank correlation between five more recent feature attribution methods and two attention-based methods, on two types of NLP tasks, and (ii) extend this analysis to also include transformer-based models. We find that attention-based explanations do not correlate strongly with any recent feature attribution methods, regardless of the model or task. Furthermore, we find that none of the tested explanations correlate strongly with one another for the transformer-based model, leading us to question the underlying assumption that we should measure the validity of attention-based explanations based on how well they correlate with existing feature attribution explanation methods. After conducting experiments on five datasets using two different models, we argue that the community should stop using rank correlation as an evaluation metric for attention-based explanations. We suggest that researchers and practitioners should instead test various explanation methods and employ a human-in-the-loop process to determine if the explanations align with human intuition for the particular use case at hand.
The remarkable success of deep learning has prompted interest in its application to medical imaging diagnosis. Even though state-of-the-art deep learning models have achieved human-level accuracy on the classification of different types of medical data, these models are hardly adopted in clinical workflows, mainly due to their lack of interpretability. The black-box-ness of deep learning models has raised the need for devising strategies to explain the decision process of these models, leading to the creation of the topic of eXplainable Artificial Intelligence (XAI). In this context, we provide a thorough survey of XAI applied to medical imaging diagnosis, including visual, textual, example-based and concept-based explanation methods. Moreover, this work reviews the existing medical imaging datasets and the existing metrics for evaluating the quality of the explanations. In addition, we include a performance comparison among a set of report generation-based methods. Finally, the major challenges in applying XAI to medical imaging and the future research directions on the topic are also discussed.
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic of active research, offering approaches to address the "how" and "why" of automated decision-making. Within this domain, counterfactual explanations (CFEs) have gained considerable traction as a psychologically grounded approach to generate post-hoc explanations. To do so, CFEs highlight what changes to a model's input would have changed its prediction in a particular way. However, despite the introduction of numerous CFE approaches, their usability has yet to be thoroughly validated at the human level. Thus, to advance the field of XAI, we introduce the Alien Zoo, an engaging, web-based and game-inspired experimental framework. The Alien Zoo provides the means to evaluate usability of CFEs for gaining new knowledge from an automated system, targeting novice users in a domain-general context. As a proof of concept, we demonstrate the practical efficacy and feasibility of this approach in a user study. Our results suggest that users benefit from receiving CFEs compared to no explanation, both in terms of objective performance in the proposed iterative learning task, and subjective usability. With this work, we aim to equip research groups and practitioners with the means to easily run controlled and well-powered user studies to complement their otherwise often more technology-oriented work. Thus, in the interest of reproducible research, we provide the entire code, together with the underlying models and user data.
Industrial Control Systems (ICSs) are becoming more and more important in managing the operation of many important systems in smart manufacturing, such as power stations, water supply systems, and manufacturing sites. While massive digital data can be a driving force for system performance, data security has raised serious concerns. Anomaly detection, therefore, is essential for preventing network security intrusions and system attacks. Many AI-based anomaly detection methods have been proposed and achieved high detection performance, however, are still a "black box" that is hard to be interpreted. In this study, we suggest using Explainable Artificial Intelligence to enhance the perspective and reliable results of an LSTM-based Autoencoder-OCSVM learning model for anomaly detection in ICS. We demonstrate the performance of our proposed method based on a well-known SCADA dataset.
The trustworthiness of neural networks is often challenged because they lack the ability to express uncertainty and explain their skill. This can be problematic given the increasing use of neural networks in high stakes decision-making such as in climate change applications. We address both issues by successfully implementing a Bayesian Neural Network (BNN), where parameters are distributions rather than deterministic, and applying novel implementations of explainable AI (XAI) techniques. The uncertainty analysis from the BNN provides a comprehensive overview of the prediction more suited to practitioners' needs than predictions from a classical neural network. Using a BNN means we can calculate the entropy (i.e. uncertainty) of the predictions and determine if the probability of an outcome is statistically significant. To enhance trustworthiness, we also spatially apply the two XAI techniques of Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanation (SHAP) values. These XAI methods reveal the extent to which the BNN is suitable and/or trustworthy. Using two techniques gives a more holistic view of BNN skill and its uncertainty, as LRP considers neural network parameters, whereas SHAP considers changes to outputs. We verify these techniques using comparison with intuition from physical theory. The differences in explanation identify potential areas where new physical theory guided studies are needed.
Dimensionality reduction (DR) is a popular method for preparing and analyzing high-dimensional data. Reduced data representations are less computationally intensive and easier to manage and visualize, while retaining a significant percentage of their original information. Aside from these advantages, these reduced representations can be difficult or impossible to interpret in most circumstances, especially when the DR approach does not provide further information about which features of the original space led to their construction. This problem is addressed by Interpretable Machine Learning, a subfield of Explainable Artificial Intelligence that addresses the opacity of machine learning models. However, current research on Interpretable Machine Learning has been focused on supervised tasks, leaving unsupervised tasks like Dimensionality Reduction unexplored. In this paper, we introduce LXDR, a technique capable of providing local interpretations of the output of DR techniques. Experiment results and two LXDR use case examples are presented to evaluate its usefulness.
We introduce Doctor XAvIer, a BERT-based diagnostic system that extracts relevant clinical data from transcribed patient-doctor dialogues and explains predictions using feature attribution methods. We present a novel performance plot and evaluation metric for feature attribution methods: Feature Attribution Dropping (FAD) curve and its Normalized Area Under the Curve (N-AUC). FAD curve analysis shows that integrated gradients outperforms Shapley values in explaining diagnosis classification. Doctor XAvIer outperforms the baseline with 0.97 F1-score in named entity recognition and symptom pertinence classification and 0.91 F1-score in diagnosis classification.