Neural Network Interpretability

Overview

Neural network interpretability asks what a model has learned, which internal computations support its predictions, and whether those computations are understandable and reliable. Post-hoc methods include saliency and attribution, concept-based explanations, counterfactuals, and formal logical explanations; mechanistic work uses probes, sparse autoencoders, circuit analysis, and interventions on neurons or features. Another approach builds interpretability into models through sparse or additive architectures, prototypes, symbolic rules, and concept bottlenecks, with evaluations spanning image, language, time-series, and scientific tasks. A central challenge is showing that an explanation is both human-meaningful and faithful to the model: readable features or sparse circuits alone do not establish causal importance, and methods can vary in robustness and reliability across settings.

Latest papers

367 papers25 papers in the last four weeks, down 43% on the four weeks before. 0.2% of all new papers.

May 29, 2025

Learning Interpretable Differentiable Logic Networks for Tabular Regression

Neural networks (NNs) achieve outstanding performance in many domains; however, their decision processes are often opaque and their inference can be computationally expensive in resource-constrained environments. We recently proposed Differentiable Logic Networks (DLNs) to address these issues for tabular classification based on relaxing discrete logic into a differentiable form, thereby enabling gradient-based learning of networks built from binary logic operations. DLNs offer interpretable reasoning and substantially lower inference cost. We extend the DLN framework to supervised tabular regression. We first redesign the final output layer (the SumLayer) to support continuous targets. More critically, we find the original two-phase training procedure used for classification is suboptimal for regression, and thus develop a unified, single-stage optimization procedure. We also demonstrate that temperature annealing of the network's differentiable relaxations is decisive for achieving stable convergence and high accuracy. We evaluate the resulting model on 15 public regression benchmarks, comparing it with modern neural networks and classical regression baselines. Regression DLNs match or exceed baseline accuracy while preserving interpretability and fast inference. Our results show that DLNs are a viable, cost-effective alternative for regression tasks, especially where model transparency and computational efficiency are important.
May 26, 2025

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks

Tensorizing a neural network involves reshaping some or all of its dense weight matrices into higher-order tensors and approximating them using low-rank tensor network decompositions. This technique has shown promise as a model compression strategy for large-scale neural networks. However, despite encouraging empirical results, tensorized neural networks (TNNs) remain underutilized in mainstream deep learning. In this position paper, we offer a perspective on both the potential and current limitations of TNNs. We argue that TNNs represent a powerful yet underexplored framework for deep learning--one that deserves greater attention from both engineering and theoretical communities. Beyond compression, we highlight the value of TNNs as a flexible class of architectures with distinctive scaling properties and increased interpretability. A central feature of TNNs is the presence of bond indices, which introduce new latent spaces not found in conventional networks. These internal representations may provide deeper insight into the evolution of features across layers, potentially advancing the goals of mechanistic interpretability. We conclude by outlining several key research directions aimed at overcoming the practical barriers to scaling and adopting TNNs in modern deep learning workflows.
May 21, 2025

Explainable embeddings with Distance Explainer

While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.
Mar 13, 2025

Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks

Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from over-parameterization, complicating interpretation and raising uncertainty issues. Bayesian neural networks (BNNs) address the latter by representing weights as probability distributions, allowing for predictive uncertainty evaluation. Latent binary Bayesian neural networks (LBBNNs) further handle structural uncertainty and sparsify models by removing redundant weights. This article advances LBBNNs by enabling covariates to skip to any succeeding layer or be excluded, simplifying networks and clarifying input impacts on predictions. This further allows us to learn simpler structures (e.g., linear or even constant intercept only models) when appropriate. Furthermore, the input-skip LBBNN (ISLaB) approach reduces network density significantly compared to standard LBBNNs, achieving over 99% reduction for small networks and over 99.9% for larger ones, while still maintaining high predictive accuracy and uncertainty quantification. For example, on MNIST, we reached 97% accuracy and great calibration with just 935 weights, reaching state-of-the-art for compression of neural networks. Furthermore, the proposed method accurately identifies the true covariates and adjusts for system non-linearity. The main contribution is the introduction of active paths, enhancing directly designed global and local explanations within the LBBNN framework. The latter are exact with theoretical guarantees and do not require post hoc external tools.
Mar 5, 2025

Exploring specialization and sensitivity of convolutional neural networks under simultaneous image augmentations

Drawing parallels with the way biological networks are studied, the authors adapt the treatment--control paradigm to explainable artificial intelligence research and enrich it through multi-parametric input alterations. A framework for investigating internal inference impacted by input data augmentations is proposed to address the real-world scenario with multiple simultaneously applied treatments instead of observing a single effect. The internal changes in network operation are reflected in activation changes measured by variance, which can be decomposed into components related to each augmentation by employing Sobol indices and Shapley values. To facilitate distinguishing model-related specifics from the self-interactions of augmentations, an auxiliary variable responsible for their permutations has been incorporated into the analysis. The resulting quantities enable one to visualize sensitivity to different variables and use them as features for further analysis and processing, including guided masking of activations. In addition, a method for single-class sensitivity analysis is introduced through a pipeline that involves class selection according to their match with the prediction bias generated by targeted damaging of the activations. Three convolutional networks, namely AlexNet, VGG11, and ResNet18, have been evaluated via the designed framework, with two vision transformers, ViT-b-16 and Swin-t, partially complementing the findings. Two sets of augmentations, consisting of five and seven distinct input transformations applied simultaneously, have been utilized as sources of variance in the image domain. Relying on the observed parallels, the authors assume that the developed framework can potentially be transferred to the study of biological neural networks in complex environments, as well as enhance the design of autonomous decision-making systems.
Feb 2, 2025

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning

Deep reinforcement learning (DRL) has successfully addressed many complex control problems. However, the neural networks representing policies or values remain opaque, undermining trust in high-stakes applications. While concept-based methods have shown promise in deciphering internal representations in computer vision, applying them to DRL is impeded by the absence of pre-defined semantic concepts in continuous state spaces. In this work, we propose a novel concept-based explanation framework designed to provide fine-grained, neuron-level insights into DRL models. Unlike previous approaches that rely on manual feature engineering, our framework automatically aligns neuron activations with logical formulas composed of semantic predicates. To bridge the gap between continuous signals and symbolic reasoning, we introduce a value-sensitive discretization mechanism that transforms raw state features into interpretable atomic concepts. This ensures that the vocabulary used for explanation captures strategic decision boundaries relevant to the agent's value assessment. By composing these interpretable concepts and matching them with neuron behaviors, we derive explicit explanations for the network's internal representations. Experimental results on both continuous and discrete environments demonstrate that our method effectively identifies meaningful decision-making patterns, offering faithful explanations that align with human intuition.
Jan 13, 2025

Derivation of effective gradient flow equations and dynamical truncation of training data in Deep Learning

We derive explicit equations governing the cumulative biases and weights in Deep Learning with ReLU activation function, based on gradient descent for the Euclidean loss in the input layer, and under the assumption that the weights are, in a precise sense, adapted to the coordinate system distinguished by the activations. We show that gradient descent corresponds to a dynamical process in the input layer, whereby clusters of data are progressively reduced in complexity ("truncated") at an exponential rate that increases with the number of data points that have already been truncated. We provide a detailed discussion of several types of solutions to the gradient flow equations. A main motivation for this work is to shed light on the interpretability question in supervised learning.