Mechanistic understanding and validation of large AI models with SemanticLens

Unlike human-engineered systems such as aeroplanes, where each component's role and dependencies are well understood, the inner workings of AI models remain largely opaque, hindering verifiability and undermining trust. This paper introduces SemanticLens, a universal explanation method for neural networks that maps hidden knowledge encoded by components (e.g., individual neurons) into the semantically structured, multimodal space of a foundation model such as CLIP. In this space, unique operations become possible, including (i) textual search to identify neurons encoding specific concepts, (ii) systematic analysis and comparison of model representations, (iii) automated labelling of neurons and explanation of their functional roles, and (iv) audits to validate decision-making against requirements. Fully scalable and operating without human input, SemanticLens is shown to be effective for debugging and validation, summarizing model knowledge, aligning reasoning with expectations (e.g., adherence to the ABCDE-rule in melanoma classification), and detecting components tied to spurious correlations and their associated training data. By enabling component-level understanding and validation, the proposed approach helps bridge the "trust gap" between AI models and traditional engineered systems. We provide code for SemanticLens on https://github.com/jim-berend/semanticlens and a demo on https://semanticlens.hhi-research-insights.eu.

Opportunities and limitations of explaining quantum machine learning

A common trait of many machine learning models is that it is often difficult to understand and explain what caused the model to produce the given output. While the explainability of neural networks has been an active field of research in the last years, comparably little is known for quantum machine learning models. Despite a few recent works analyzing some specific aspects of explainability, as of now there is no clear big picture perspective as to what can be expected from quantum learning models in terms of explainability. In this work, we address this issue by identifying promising research avenues in this direction and lining out the expected future results. We additionally propose two explanation methods designed specifically for quantum machine learning models, as first of their kind to the best of our knowledge. Next to our pre-view of the field, we compare both existing and novel methods to explain the predictions of quantum learning models. By studying explainability in quantum machine learning, we can contribute to the sustainable development of the field, preventing trust issues in the future.

Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond

In recent years, training data attribution (TDA) methods have emerged as a promising direction for the interpretability of neural networks. While research around TDA is thriving, limited effort has been dedicated to the evaluation of attributions. Similar to the development of evaluation metrics for traditional feature attribution approaches, several standalone metrics have been proposed to evaluate the quality of TDA methods across various contexts. However, the lack of a unified framework that allows for systematic comparison limits trust in TDA methods and stunts their widespread adoption. To address this research gap, we introduce Quanda, a Python toolkit designed to facilitate the evaluation of TDA methods. Beyond offering a comprehensive set of evaluation metrics, Quanda provides a uniform interface for seamless integration with existing TDA implementations across different repositories, thus enabling systematic benchmarking. The toolkit is user-friendly, thoroughly tested, well-documented, and available as an open-source library on PyPi and under https://github.com/dilyabareeva/quanda.

PINNfluence: Influence Functions for Physics-Informed Neural Networks

Recently, physics-informed neural networks (PINNs) have emerged as a flexible and promising application of deep learning to partial differential equations in the physical sciences. While offering strong performance and competitive inference speeds on forward and inverse problems, their black-box nature limits interpretability, particularly regarding alignment with expected physical behavior. In the present work, we explore the application of influence functions (IFs) to validate and debug PINNs post-hoc. Specifically, we apply variations of IF-based indicators to gauge the influence of different types of collocation points on the prediction of PINNs applied to a 2D Navier-Stokes fluid flow problem. Our results demonstrate how IFs can be adapted to PINNs to reveal the potential for further studies.

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of these often over-parameterized networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion. We extend the current state by proposing to explicitly optimize hyperparameters of attribution methods for the task of pruning, and further include transformer-based networks in our analysis. Our approach yields higher model compression rates of large transformer- and convolutional architectures (VGG, ResNet, ViT) compared to previous works, while still attaining high performance on ImageNet classification tasks. Here, our experiments indicate that transformers have a higher degree of over-parameterization compared to convolutional neural networks. Code is available at $\href{https://github.com/erfanhatefi/Pruning-by-eXplaining-in-PyTorch}{\text{this https link}}$.

DualView: Data Attribution from the Dual Perspective

Local data attribution (or influence estimation) techniques aim at estimating the impact that individual data points seen during training have on particular predictions of an already trained Machine Learning model during test time. Previous methods either do not perform well consistently across different evaluation criteria from literature, are characterized by a high computational demand, or suffer from both. In this work we present DualView, a novel method for post-hoc data attribution based on surrogate modelling, demonstrating both high computational efficiency, as well as good evaluation results. With a focus on neural networks, we evaluate our proposed technique using suitable quantitative evaluation strategies from the literature against related principal local data attribution methods. We find that DualView requires considerably lower computational resources than other methods, while demonstrating comparable performance to competing approaches across evaluation metrics. Futhermore, our proposed method produces sparse explanations, where sparseness can be tuned via a hyperparameter. Finally, we showcase that with DualView, we can now render explanations from local data attributions compatible with established local feature attribution methods: For each prediction on (test) data points explained in terms of impactful samples from the training set, we are able to compute and visualize how the prediction on (test) sample relates to each influential training sample in terms of features recognized and by the model. We provide an Open Source implementation of DualView online, together with implementations for all other local data attribution methods we compare against, as well as the metrics reported here, for full reproducibility.

AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers

Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box transformer model and maintaining computational efficiency is an unsolved challenge. By extending the Layer-wise Relevance Propagation attribution method to handle attention layers, we address these challenges effectively. While partial solutions exist, our method is the first to faithfully and holistically attribute not only input but also latent representations of transformer models with the computational efficiency similar to a singular backward pass. Through extensive evaluations against existing methods on Llama 2, Flan-T5 and the Vision Transformer architecture, we demonstrate that our proposed approach surpasses alternative methods in terms of faithfulness and enables the understanding of latent representations, opening up the door for concept-based explanations. We provide an open-source implementation on GitHub https://github.com/rachtibat/LRP-for-Transformers.

Layer-wise Feedback Propagation

In this paper, we present Layer-wise Feedback Propagation (LFP), a novel training approach for neural-network-like predictors that utilizes explainability, specifically Layer-wise Relevance Propagation(LRP), to assign rewards to individual connections based on their respective contributions to solving a given task. This differs from traditional gradient descent, which updates parameters towards anestimated loss minimum. LFP distributes a reward signal throughout the model without the need for gradient computations. It then strengthens structures that receive positive feedback while reducingthe influence of structures that receive negative feedback. We establish the convergence of LFP theoretically and empirically, and demonstrate its effectiveness in achieving comparable performance to gradient descent on various models and datasets. Notably, LFP overcomes certain limitations associated with gradient-based methods, such as reliance on meaningful derivatives. We further investigate how the different LRP-rules can be extended to LFP, what their effects are on training, as well as potential applications, such as training models with no meaningful derivatives, e.g., step-function activated Spiking Neural Networks (SNNs), or for transfer learning, to efficiently utilize existing knowledge.

Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations

Applying traditional post-hoc attribution methods to segmentation or object detection predictors offers only limited insights, as the obtained feature attribution maps at input level typically resemble the models' predicted segmentation mask or bounding box. In this work, we address the need for more informative explanations for these predictors by proposing the post-hoc eXplainable Artificial Intelligence method L-CRP to generate explanations that automatically identify and visualize relevant concepts learned, recognized and used by the model during inference as well as precisely locate them in input space. Our method therefore goes beyond singular input-level attribution maps and, as an approach based on the recently published Concept Relevance Propagation technique, is efficiently applicable to state-of-the-art black-box architectures in segmentation and object detection, such as DeepLabV3+ and YOLOv6, among others. We verify the faithfulness of our proposed technique by quantitatively comparing different concept attribution methods, and discuss the effect on explanation complexity on popular datasets such as CityScapes, Pascal VOC and MS COCO 2017. The ability to precisely locate and communicate concepts is used to reveal and verify the use of background features, thereby highlighting possible biases of the model.

From "Where" to "What": Towards Human-Understandable Explanations through Concept Relevance Propagation

The emerging 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. Only few contemporary techniques aim at combining the principles behind both local and global XAI for obtaining more informative explanations. Those methods, however, are often limited to specific model architectures or impose additional requirements on training regimes or data and label availability, which renders the post-hoc application to arbitrarily pre-trained models practically impossible. In this work we introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives of XAI and thus allows answering both the "where" and "what" questions for individual predictions, without additional constraints imposed. We further introduce the principle of Relevance Maximization for finding representative examples of encoded concepts based on their usefulness to the model. We thereby lift the dependency on the common practice of Activation Maximization and its limitations. We demonstrate the capabilities of our methods in various settings, showcasing that Concept Relevance Propagation and Relevance Maximization lead to more human interpretable explanations and provide deep insights into the model's representations and reasoning through concept atlases, concept composition analyses, and quantitative investigations of concept subspaces and their role in fine-grained decision making.