Research Papers

Model interpretability is a key challenge that has yet to align with the advancements observed in contemporary state-of-the-art deep learning models. In particular, deep learning aided vision tasks require interpretability, in order for their adoption in more specialized domains such as medical imaging. Although the field of explainable AI (XAI) developed methods for interpreting vision models along with early convolutional neural networks, recent XAI research has mainly focused on assigning attributes via saliency maps. As such, these methods are restricted to providing explanations at a sample level, and many explainability methods suffer from low adaptability across a wide range of vision models. In our work, we re-think vision-model explainability from a novel perspective, to probe the general input structure that a model has learnt during its training. To this end, we ask the question: "How would a vision model fill-in a masked-image". Experiments on standard vision datasets and pre-trained models reveal consistent patterns, and could be intergrated as an additional model-agnostic explainability tool in modern machine-learning platforms. The code will be available at \url{https://github.com/BoTZ-TND/FillingTheBlanks.git}

In explanations, explainers have mental representations of explainees' developing knowledge and shifting interests regarding the explanandum. These mental representations are dynamic in nature and develop over time, thereby enabling explainers to react to explainees' needs by adapting and customizing the explanation. XAI should be able to react to explainees' needs in a similar manner. Therefore, a component that incorporates aspects of explainers' mental representations of explainees is required. In this study, we took first steps by investigating explainers' mental representations in everyday explanations of technological artifacts. According to the dual nature theory, technological artifacts require explanations with two distinct perspectives, namely observable and measurable features addressing "Architecture" or interpretable aspects addressing "Relevance". We conducted extended semi structured pre-, post- and video recall-interviews with explainers (N=9) in the context of an explanation. The transcribed interviews were analyzed utilizing qualitative content analysis. The explainers' answers regarding the explainees' knowledge and interests with regard to the technological artifact emphasized the vagueness of early assumptions of explainers toward strong beliefs in the course of explanations. The assumed knowledge of explainees in the beginning is centered around Architecture and develops toward knowledge with regard to both Architecture and Relevance. In contrast, explainers assumed higher interests in Relevance in the beginning to interests regarding both Architecture and Relevance in the further course of explanations. Further, explainers often finished the explanation despite their perception that explainees still had gaps in knowledge. These findings are transferred into practical implications relevant for user models for adaptive explainable systems.

This study presents DhondtXAI as a SHAP-independent, D'Hondt-based attribution framework for tabular XAI. Instead of model-native feature importance or SHAP values, DhondtXAI computes background-interventional removal effects, separates positive and negative evidence, forms optional feature alliances, applies optional thresholds, allocates seats via the D'Hondt rule, and projects onto the local model-output difference. Completeness is preserved by construction, with the projection residual ratio reported as a diagnostic. The method is evaluated on synthetic additive and interaction tests, correlated-feature perturbations, operator and apportionment ablations, projection-mode comparisons, logit-scale checks, repeated split validation, paired deletion tests, and two healthcare datasets: Wisconsin Diagnostic Breast Cancer (CatBoost) and early-stage diabetes risk prediction (XGBoost). SHAP serves only as an external comparator with aligned settings. In additive synthetics, DhondtXAI exactly recovers ground-truth rankings; in multiplicative interactions, alliances reduce the mean projection residual from 0.2527 to 0.0001. On WDBC and diabetes data, it shows high agreement with SHAP (Spearman rho = 0.9273 and 0.9353), supported by further signed, top-k, magnitude, deletion, and sensitivity analyses. Results position DhondtXAI as a complementary proportional, alliance-aware, and threshold-aware tabular XAI method, not a replacement for SHAP or LIME.

Understanding node representations in graph-based models is crucial for uncovering biases ,diagnosing errors, and building trust in model decisions. However, previous work on explainable AI for node representations has primarily emphasized explanations (reasons for model predictions) rather than interpretations (mapping representations to understandable concepts). Furthermore, the limited research that focuses on interpretation lacks validation, and thus the reliability of such methods is unclear. We address this gap by proposing a novel interpretation method-Node Coherence Rate for Representation Interpretation (NCI)-which quantifies how well different node relations are captured in node representations. We also propose a novel method (IME) to evaluate the accuracy of different interpretation methods. Our experimental results demonstrate that NCI reduces the error of the previous best approach by an average of 39%. We then apply NCI to derive insights about the node representations produced by several graph-based methods and assess their quality in unsupervised settings.

Providing human-understandable insights into the inner workings of neural networks is an important step toward achieving more explainable and trustworthy AI. Existing approaches to such mechanistic interpretability typically require substantial prior knowledge and manual effort, with strategies tailored to specific tasks. In this work, we take a step toward automating the understanding of the network by investigating the existence of distinct sub-networks. Specifically, we explore a novel automated and task-agnostic approach based on the notion of functionally similar representations within neural networks to identify similar and dissimilar layers, revealing potential sub-networks. We achieve this by proposing, for the first time to our knowledge, the use of Gromov-Wasserstein distance, which overcomes challenges posed by varying distributions and dimensionalities across intermediate representations, issues that complicate direct layer to layer comparisons. On algebraic, language, and vision tasks, we observe the emergence of sub-groups within neural network layers corresponding to functional abstractions. Through downstream applications of model compression and fine-tuning, we show the proposed approach offers meaningful insights into the behavior of neural networks with minimal human and computational cost.

The burgeoning field of Natural Language Processing (NLP) stands at a critical juncture where the integration of fairness within its frameworks has become an imperative. This PhD thesis addresses the need for equity and transparency in NLP systems, recognizing that fairness in NLP is not merely a technical challenge but a moral and ethical necessity, requiring a rigorous examination of how these technologies interact with and impact diverse human populations. Through this lens, this thesis undertakes a thorough investigation into the development of equitable NLP methodologies and the evaluation of biases that prevail in current systems. First, it introduces an innovative algorithm to mitigate biases in multi-class classifiers, tailored for high-risk NLP applications, surpassing traditional methods in both bias mitigation and prediction accuracy. Then, an analysis of the Bios dataset reveals the impact of dataset size on discriminatory biases and the limitations of standard fairness metrics. This awareness has led to explorations in the field of explainable AI, aiming for a more complete understanding of biases where traditional metrics are limited. Consequently, the thesis presents COCKATIEL, a model-agnostic explainability method that identifies and ranks concepts in Transformer models, outperforming previous approaches in sentiment analysis tasks. Finally, the thesis contributes to bridging the gap between fairness and explainability by introducing TaCo, a novel method to neutralize bias in Transformer model embeddings. In conclusion, this thesis constitutes a significant interdisciplinary endeavor that intertwines explicability and fairness to challenge and reshape current NLP paradigms. The methodologies and critiques presented contribute to the ongoing discourse on fairness in machine learning, offering actionable solutions for more equitable and responsible AI systems.

Federated learning (FL) is a commonly distributed algorithm for mobile users (MUs) training artificial intelligence (AI) models, however, several challenges arise when applying FL to real-world scenarios, such as label scarcity, non-IID data, and unexplainability. As a result, we propose an explainable personalized FL framework, called XPFL. First, we introduce a generative AI (GAI) assisted personalized federated semi-supervised learning, called GFed. Particularly, in local training, we utilize a GAI model to learn from large unlabeled data and apply knowledge distillation-based semi-supervised learning to train the local FL model using the knowledge acquired from the GAI model. In global aggregation, we obtain the new local FL model by fusing the local and global FL models in specific proportions, allowing each local model to incorporate knowledge from others while preserving its personalized characteristics. Second, we propose an explainable AI mechanism for FL, named XFed. Specifically, in local training, we apply a decision tree to match the input and output of the local FL model. In global aggregation, we utilize t-distributed stochastic neighbor embedding (t-SNE) to visualize the local models before and after aggregation. Finally, simulation results validate the effectiveness of the proposed XPFL framework.

The ability to steer AI behavior is crucial to preventing its long term dangerous and catastrophic potential. Representation Engineering (RepE) has emerged as a novel, powerful method to steer internal model behaviors, such as "honesty", at a top-down level. Understanding the steering of representations should thus be placed at the forefront of alignment initiatives. Unfortunately, current efforts to understand plasticity at this level are highly neglected. This paper aims to bridge the knowledge gap and understand how LLM representation stability, specifically for the concept of "honesty", and model plasticity evolve by applying steering vectors extracted at different fine-tuning stages, revealing differing magnitudes of shifts in model behavior. The findings are pivotal, showing that while early steering exhibits high plasticity, later stages have a surprisingly responsive critical window. This pattern is observed across different model architectures, signaling that there is a general pattern of model plasticity that can be used for effective intervention. These insights greatly contribute to the field of AI transparency, addressing a pressing lack of efficiency limiting our ability to effectively steer model behavior.

Introduction Schizophrenia is a severe mental disorder, and early diagnosis is key to improving outcomes. Its complexity makes predicting onset and progression challenging. EEG has emerged as a valuable tool for studying schizophrenia, with machine learning increasingly applied for diagnosis. This paper assesses the accuracy of ML models for predicting schizophrenia and examines the impact of stress during EEG recording on model performance. We integrate acute stress prediction into the analysis, showing that overlapping conditions like stress during recording can negatively affect model accuracy. Methods Four XGBoost models were built: one for stress prediction, two to classify schizophrenia (at rest and task), and a model to predict schizophrenia for both conditions. XAI techniques were applied to analyze results. Experiments tested the generalization of schizophrenia models using their datasets' healthy controls and independent health-screened controls. The stress model identified high-stress subjects, who were excluded from further analysis. A novel method was used to adjust EEG frequency band power to remove stress artifacts, improving predictive model performance. Results Our results show that acute stress vary across EEG sessions, affecting model performance and accuracy. Generalization improved once these varying stress levels were considered and compensated for during model training. Our findings highlight the importance of thorough health screening and management of the patient's condition during the process. Stress induced during or by the EEG recording can adversely affect model generalization. This may require further preprocessing of data by treating stress as an additional physiological artifact. Our proposed approach to compensate for stress artifacts in EEG data used for training models showed a significant improvement in predictive performance.

Integrating Reasoning Systems for Trustworthy AI, Proceedings of the 4th Workshop on Logic and Practice of Programming (LPOP)

Anil Nerode, Yanhong A. Liu

This proceedings contains abstracts and position papers for the work to be presented at the fourth Logic and Practice of Programming (LPOP) Workshop. The workshop is to be held in Dallas, Texas, USA, and as a hybrid event, on October 13, 2024, in conjunction with the 40th International Conference on Logic Programming (ICLP). The focus of this workshop is integrating reasoning systems for trustworthy AI, especially including integrating diverse models of programming with rules and constraints.

Explaining Explaining

Sergei Nirenburg, Marjorie McShane, Kenneth W. Goodman +1

Explanation is key to people having confidence in high-stakes AI systems. However, machine-learning-based systems -- which account for almost all current AI -- can't explain because they are usually black boxes. The explainable AI (XAI) movement hedges this problem by redefining "explanation". The human-centered explainable AI (HCXAI) movement identifies the explanation-oriented needs of users but can't fulfill them because of its commitment to machine learning. In order to achieve the kinds of explanations needed by real people operating in critical domains, we must rethink how to approach AI. We describe a hybrid approach to developing cognitive agents that uses a knowledge-based infrastructure supplemented by data obtained through machine learning when applicable. These agents will serve as assistants to humans who will bear ultimate responsibility for the decisions and actions of the human-robot team. We illustrate the explanatory potential of such agents using the under-the-hood panels of a demonstration system in which a team of simulated robots collaborate on a search task assigned by a human.

For automatic human figure drawing (HFD) assessment tasks, such as diagnosing autism spectrum disorder (ASD) using HFD images, the clarity and explainability of a model decision are crucial. Existing pixel-level attribution-based explainable AI (XAI) approaches demand considerable effort from users to interpret the semantic information of a region in an image, which can be often time-consuming and impractical. To overcome this challenge, we propose a part contribution evaluation based model explanation (PCEvE) framework. On top of the part detection, we measure the Shapley Value of each individual part to evaluate the contribution to a model decision. Unlike existing attribution-based XAI approaches, the PCEvE provides a straightforward explanation of a model decision, i.e., a part contribution histogram. Furthermore, the PCEvE expands the scope of explanations beyond the conventional sample-level to include class-level and task-level insights, offering a richer, more comprehensive understanding of model behavior. We rigorously validate the PCEvE via extensive experiments on multiple HFD assessment datasets. Also, we sanity-check the proposed method with a set of controlled experiments. Additionally, we demonstrate the versatility and applicability of our method to other domains by applying it to a photo-realistic dataset, the Stanford Cars.