Research Papers

In the domain of unsupervised image-to-image transformation using generative transformative models, CycleGAN has become the architecture of choice. One of the primary downsides of this architecture is its relatively slow rate of convergence. In this work, we use discriminator-driven explainability to speed up the convergence rate of the generative model by using saliency maps from the discriminator that mask the gradients of the generator during backpropagation, based on the work of Nagisetty et al., and also introducing the saliency map on input, added onto a Gaussian noise mask, by using an interpretable latent variable based on Wang M.'s Mask CycleGAN. This allows for an explainability fusion in both directions, and utilizing the noise-added saliency map on input as evidence-based counterfactual filtering. This new architecture has much higher rate of convergence than a baseline CycleGAN architecture while preserving the image quality.

Investigating deep learning language models has always been a significant research area due to the ``black box" nature of most advanced models. With the recent advancements in pre-trained language models based on transformers and their increasing integration into daily life, addressing this issue has become more pressing. In order to achieve an explainable AI model, it is essential to comprehend the procedural steps involved and compare them with human thought processes. Thus, in this paper, we use simple, well-understood non-language tasks to explore these models' inner workings. Specifically, we apply a pre-trained language model to constrained arithmetic problems with hierarchical structure, to analyze their attention weight scores and hidden states. The investigation reveals promising results, with the model addressing hierarchical problems in a moderately structured manner, similar to human problem-solving strategies. Additionally, by inspecting the attention weights layer by layer, we uncover an unconventional finding that layer 10, rather than the model's final layer, is the optimal layer to unfreeze for the least parameter-intensive approach to fine-tune the model. We support these findings with entropy analysis and token embeddings similarity analysis. The attention analysis allows us to hypothesize that the model can generalize to longer sequences in ListOps dataset, a conclusion later confirmed through testing on sequences longer than those in the training set. Lastly, by utilizing a straightforward task in which the model predicts the winner of a Tic Tac Toe game, we identify limitations in attention analysis, particularly its inability to capture 2D patterns.

With the growing concern for air quality and its impact on human health, interest in environmental gas monitoring has increased. However, chemi-resistive gas sensing devices are plagued by issues of sensor reproducibility during manufacturing. This study proposes a novel approach for detecting sensor-to-sensor variations in sensing devices using the explainable AI (XAI) method of SHapley Additive exPlanations (SHAP). This is achieved by identifying sensors that contribute the most to environmental gas concentration estimation via machine learning, and measuring the similarity of feature rankings between sensors to flag deviations or outliers. The methodology is tested using artificial and realistic Ozone concentration profiles to train a Gated Recurrent Unit (GRU) model. Two applications were explored in the study: the detection of wrong behaviors of sensors in the train dataset, and the detection of deviations in the test dataset. By training the GRU with the pruned train dataset, we could reduce computational costs while improving the model performance. Overall, the results show that our approach improves the understanding of sensor behavior, successfully detects sensor deviations down to 5-10% from the normal behavior, and leads to more efficient model preparation and calibration. Our method provides a novel solution for identifying deviating sensors, linking inconsistencies in hardware to sensor-to-sensor variations in the manufacturing process on an AI model-level.

Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability

E. Zhixuan Zeng, Hayden Gunraj, Sheldon Fernandez +1

Explainability plays a crucial role in providing a more comprehensive understanding of deep learning models' behaviour. This allows for thorough validation of the model's performance, ensuring that its decisions are based on relevant visual indicators and not biased toward irrelevant patterns existing in training data. However, existing methods provide only instance-level explainability, which requires manual analysis of each sample. Such manual review is time-consuming and prone to human biases. To address this issue, the concept of second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. SOXAI automates the analysis of the connections between quantitative explanations and dataset biases by identifying prevalent concepts. In this work, we explore the use of this higher-level interpretation of a deep neural network's behaviour to allows us to "explain the explainability" for actionable insights. Specifically, we demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.

Progress in graph neural networks has grown rapidly in recent years, with many new developments in drug discovery, medical diagnosis, and recommender systems. While this progress is significant, many networks are `black boxes' with little understanding of the `what' exactly the network is learning. Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models so that users can recognize errors and discover new knowledge. Therefore, the development of explainable AI algorithms is essential for us to reap the benefits of AI. We propose an explainability algorithm for GNNs called eXplainable Insight (XInsight) that generates a distribution of model explanations using GFlowNets. Since GFlowNets generate objects with probabilities proportional to a reward, XInsight can generate a diverse set of explanations, compared to previous methods that only learn the maximum reward sample. We demonstrate XInsight by generating explanations for GNNs trained on two graph classification tasks: classifying mutagenic compounds with the MUTAG dataset and classifying acyclic graphs with a synthetic dataset that we have open-sourced. We show the utility of XInsight's explanations by analyzing the generated compounds using QSAR modeling, and we find that XInsight generates compounds that cluster by lipophilicity, a known correlate of mutagenicity. Our results show that XInsight generates a distribution of explanations that uncovers the underlying relationships demonstrated by the model. They also highlight the importance of generating a diverse set of explanations, as it enables us to discover hidden relationships in the model and provides valuable guidance for further analysis.

In this survey paper, we deep dive into the field of Explainable Artificial Intelligence (XAI). After introducing the scope of this paper, we start by discussing what an "explanation" really is. We then move on to discuss some of the existing approaches to XAI and build a taxonomy of the most popular methods. Next, we also look at a few applications of these and other XAI techniques in four primary domains: finance, autonomous driving, healthcare and manufacturing. We end by introducing a promising discipline, "Explanation Engineering," which includes a systematic approach for designing explainability into AI systems.

Machine learning (ML) is successful in achieving human-level artificial intelligence in various fields. However, it lacks the ability to explain an outcome due to its black-box nature. While recent efforts on explainable AI (XAI) has received significant attention, most of the existing solutions are not applicable in real-time systems since they map interpretability as an optimization problem, which leads to numerous iterations of time-consuming complex computations. Although there are existing hardware-based acceleration framework for XAI, they are implemented through FPGA and designed for specific tasks, leading to expensive cost and lack of flexibility. In this paper, we propose a simple yet efficient framework to accelerate various XAI algorithms with existing hardware accelerators. Specifically, this paper makes three important contributions. (1) The proposed method is the first attempt in exploring the effectiveness of Tensor Processing Unit (TPU) to accelerate XAI. (2) Our proposed solution explores the close relationship between several existing XAI algorithms with matrix computations, and exploits the synergy between convolution and Fourier transform, which takes full advantage of TPU's inherent ability in accelerating matrix computations. (3) Our proposed approach can lead to real-time outcome interpretation. Extensive experimental evaluation demonstrates that proposed approach deployed on TPU can provide drastic improvement in interpretation time (39x on average) as well as energy efficiency (69x on average) compared to existing acceleration techniques.

Air Traffic Management data systems today are inefficient and not scalable to enable future unmanned systems. Current data is fragmented, siloed, and not easily accessible. There is data conflict, misuse, and eroding levels of trust in provenance and accuracy. With increased autonomy in aviation, Artificially Intelligent (AI) enabled unmanned traffic management (UTM) will be more reliant on secure data from diverse stakeholders. There is an urgent need to develop a secure network that has trustworthy data chains and works with the requirements generated by UTM. Here, we review existing research in 3 key interconnected areas: (1) blockchain development for secure data transfer between competing aviation stakeholders, (2) self-learning networking architectures that distribute consensus to achieve secure air traffic control, (3) explainable AI to build trust with human stakeholders and backpropagate requirements for blockchain and network optimisation. When connected together, this new digital ecosystem blueprint is tailored for safety critical UTM sectors. We motivate the readers with a case study, where a federated learning UTM uses real air traffic and weather data is secured and explained to human operators. This emerging area still requires significant research and development by the community to ensure it can enable future autonomous air mobility.

Local Interpretability of Random Forests for Multi-Target Regression

Avraam Bardos, Nikolaos Mylonas, Ioannis Mollas +1

Multi-target regression is useful in a plethora of applications. Although random forest models perform well in these tasks, they are often difficult to interpret. Interpretability is crucial in machine learning, especially when it can directly impact human well-being. Although model-agnostic techniques exist for multi-target regression, specific techniques tailored to random forest models are not available. To address this issue, we propose a technique that provides rule-based interpretations for instances made by a random forest model for multi-target regression, influenced by a recent model-specific technique for random forest interpretability. The proposed technique was evaluated through extensive experiments and shown to offer competitive interpretations compared to state-of-the-art techniques.

Monetizing Explainable AI: A Double-edged Sword

Travis Greene, Sofie Goethals, David Martens +1

Algorithms used by organizations increasingly wield power in society as they decide the allocation of key resources and basic goods. In order to promote fairer, juster, and more transparent uses of such decision-making power, explainable artificial intelligence (XAI) aims to provide insights into the logic of algorithmic decision-making. Despite much research on the topic, consumer-facing applications of XAI remain rare. A central reason may be that a viable platform-based monetization strategy for this new technology has yet to be found. We introduce and describe a novel monetization strategy for fusing algorithmic explanations with programmatic advertising via an explanation platform. We claim the explanation platform represents a new, socially-impactful, and profitable form of human-algorithm interaction and estimate its potential for revenue generation in the high-risk domains of finance, hiring, and education. We then consider possible undesirable and unintended effects of monetizing XAI and simulate these scenarios using real-world credit lending data. Ultimately, we argue that monetizing XAI may be a double-edged sword: while monetization may incentivize industry adoption of XAI in a variety of consumer applications, it may also conflict with the original legal and ethical justifications for developing XAI. We conclude by discussing whether there may be ways to responsibly and democratically harness the potential of monetized XAI to provide greater consumer access to algorithmic explanations.

Contextual utility theory integrates context-sensitive factors into utility-based decision-making models. It stresses the importance of understanding individual decision-makers' preferences, values, and beliefs and the situational factors that affect them. Contextual utility theory benefits explainable AI. First, it can improve transparency and understanding of how AI systems affect decision-making. It can reveal AI model biases and limitations by considering personal preferences and context. Second, contextual utility theory can make AI systems more personalized and adaptable to users and stakeholders. AI systems can better meet user needs and values by incorporating demographic and cultural data. Finally, contextual utility theory promotes ethical AI development and social responsibility. AI developers can create ethical systems that benefit society by considering contextual factors like societal norms and values. This work, demonstrates how contextual utility theory can improve AI system transparency, personalization, and ethics, benefiting both users and developers.

The explainability of AI has transformed from a purely technical issue to a complex issue closely related to algorithmic governance and algorithmic security. The lack of explainable AI (XAI) brings adverse effects that can cross all economic classes and national borders. Despite efforts in governance, technical, and policy exchange have been made in XAI by multiple stakeholders, including the public sector, enterprises, and international organizations, respectively. XAI is still in its infancy. Future applications and corresponding regulatory instruments are still dependent on the collaborative engagement of all parties.