Graph Neural Networks (GNNs) have become increasingly popular for effectively modeling graph-structured data, and attention mechanisms have been pivotal in enabling these models to capture complex patterns. In our study, we reveal a critical yet underexplored consequence of integrating attention into edge-featured GNNs: the emergence of Massive Activations (MAs) within attention layers. By developing a novel method for detecting MAs on edge features, we show that these extreme activations are not only activation anomalies but encode domain-relevant signals. Our post-hoc interpretability analysis demonstrates that, in molecular graphs, MAs aggregate predominantly on common bond types (e.g., single and double bonds) while sparing more informative ones (e.g., triple bonds). Furthermore, our ablation studies confirm that MAs can serve as natural attribution indicators, reallocating to less informative edges. Our study assesses various edge-featured attention-based GNN models using benchmark datasets, including ZINC, TOX21, and PROTEINS. Key contributions include (1) establishing the direct link between attention mechanisms and MAs generation in edge-featured GNNs, (2) developing a robust definition and detection method for MAs enabling reliable post-hoc interpretability. Overall, our study reveals the complex interplay between attention mechanisms, edge-featured GNNs model, and MAs emergence, providing crucial insights for relating GNNs internals to domain knowledge.
Efficient Neural Networks with Discrete Cosine Transform Activations
Centre Tecnològic de Telecomunicacions de Catalunya, Spain（西班牙加泰罗尼亚电信技术中心）；Dept. of Signal Theory and Communications, Universitat Politècnica de Catalunya, Spain（西班牙加泰罗尼亚理工大学信号理论与通信系）；ICREA Acadèmia, Spain（西班牙ICREA学术机构）
The auditory attention decoding (AAD) approach was proposed to determine the identity of the attended talker in a multi-talker scenario by analyzing electroencephalography (EEG) data. Although the linear model-based method has been widely used in AAD, the linear assumption was considered oversimplified and the decoding accuracy remained lower for shorter decoding windows. Recently, nonlinear models based on deep neural networks (DNN) have been proposed to solve this problem. However, these models did not fully utilize both the spatial and temporal features of EEG, and the interpretability of D…
University of Trento（特伦托大学）；Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会（FBK））；Centro Interdipartimentale Mente e Cervello (CIMeC)（跨部门心智与大脑中心（CIMeC））
Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors, low signal to noise ratios, and the high dimensionality of neuroimaging data. Therefore, improving the interpretability of brain decoding approaches is of primary interest in many neuroimaging studies. Despite extensive studies of this type, at present, there is no formal definition for interpretability of multivariate brain maps. As a consequence, there is…
Tel-Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）
The problem of maximum likelihood decoding with a neural decoder for error-correcting code is considered. It is shown that the neural decoder can be improved with two novel loss terms on the node's activations. The first loss term imposes a sparse constraint on the node's activations. Whereas, the second loss term tried to mimic the node's activations from a teacher decoder which has better performance. The proposed method has the same run time complexity and model size as the neural Belief Propagation decoder, while improving the decoding performance by up to $1.1dB$ on BCH codes.
Circuit Insights: Towards Interpretability Beyond Activations
Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute（人工智能系，弗劳恩霍夫海因里希·赫兹研究所）；Department of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学系，柏林技术大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Centre of eXplainable Artificial Intelligence, Technological University Dublin（可解释人工智能中心，都柏林技术大学）
UCSF（加州大学旧金山分校）；SFVAMC（旧金山退伍军人事务医疗中心）；UC Berkeley（加州大学伯克利分校）；Helen Diller Family Comprehensive Cancer Center, UCSF（加州大学旧金山分校海伦·迪勒家族综合癌症中心）；Bakar Computational Health Sciences Institute, UCSF（加州大学旧金山分校巴卡尔计算健康科学研究所）
Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution dominate the interpretability literature, but these methods do not address semantic concepts such as the textures, colors, or genders of objects within an image. Our proposed Robust Concept Activation Vectors (RCAV) quantifies the effects of semantic concepts on individual model predictions and on model behavior as a whole. RCAV calculates a concept gradient and …
MIT（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
Interpreting machine learning models is challenging but crucial for ensuring the safety of deep networks in autonomous driving systems. Due to the prevalence of deep learning based perception models in autonomous vehicles, accurately interpreting their predictions is crucial. While a variety of such methods have been proposed, most are shown to lack robustness. Yet, little has been done to provide certificates for interpretability robustness. Taking a step in this direction, we present CORGI, short for Certifiably prOvable Robustness Guarantees for Interpretability mapping. CORGI is an algorit…
State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks and their opaqueness. The former raises concerns about the security and generalization of DNNs in real-world conditions, whereas the latter impedes users' trust in their output. In this research, we (1) examine the effect of adversarial robustness on interpretability and (2) present a novel approach for improving the interpretability of DNNs that is based o…
Mechanistic Interpretability of Fine-Tuned Vision Transformers on Distorted Images: Decoding Attention Head Behavior for Transparent and Trustworthy AI
Krembil Research Institute, University Health Network（肯贝尔研究所，大学健康网络）
CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability
School of Physics, Mathematics, and Computing（物理、数学与计算学院）；University of Western Australia（西澳大学）；Hefei University of Technology（合肥工业大学）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Stevens Institute of Technology（史蒂文斯理工学院）
InverseScope: Scalable Activation Inversion for Interpreting Large Language Models
School of Mathematical Science, Peking University（北京大学数学科学学院）；School of Science, Westlake University（西湖大学理学院）；Beijing International Center for Mathematical Research（北京国际数学研究中心）；New Cornerstone Science Laboratory, Peking University（北京大学新基石科学实验室）
Few-shot learning addresses problems for which a limited number of training examples are available. So far, the field has been mostly driven by applications in computer vision. Here, we are interested in adapting recently introduced few-shot methods to solve problems dealing with neuroimaging data, a promising application field. To this end, we create a neuroimaging benchmark dataset for few-shot learning and compare multiple learning paradigms, including meta-learning, as well as various backbone networks. Our experiments show that few-shot methods are able to efficiently decode brain signals…
Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
Computer Systems Engineering Dpt., Universidad Politécnica de Madrid, Madrid (Spain)（马德里理工大学计算机系统工程系）；Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul (Korea)（首尔科学技术大学计算机科学与工程系）
本研究评估了时间序列基础模型 MOMENT 在可视化分析任务中潜在空间的解释性，发现微调虽降低了损失但嵌入空间可解释性改善有限，指出基础模型仍需方法改进但显著提升了交互分析效率。
Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
Department of Computer Science, University of Maryland, College Park, United States（计算机科学系，马里兰大学，College Park，美国）；Department of Electrical and Computer Engineering, University of Maryland, College Park, United States（电气与计算机工程系，马里兰大学，College Park，美国）
INRIA Saclay-Île-de-France（法国国家信息与自动化研究所 萨克莱-法兰西岛分院）；CEA（法国原子能和替代能源委员会）；INRIA Paris - Rocquencourt（法国国家信息与自动化研究所 巴黎-罗克库尔分院）；Institut Mines-Télécom（法国国立矿业电信学院）；Télécom ParisTech（巴黎高等电信学院）；CNRS（法国国家科学研究中心）
Extracting activation patterns from functional Magnetic Resonance Images (fMRI) datasets remains challenging in rapid-event designs due to the inherent delay of blood oxygen level-dependent (BOLD) signal. The general linear model (GLM) allows to estimate the activation from a design matrix and a fixed hemodynamic response function (HRF). However, the HRF is known to vary substantially between subjects and brain regions. In this paper, we propose a model for jointly estimating the hemodynamic response function (HRF) and the activation patterns via a low-rank representation of task effects.This …
We describe an "interpretability illusion" that arises when analyzing the BERT model. Activations of individual neurons in the network may spuriously appear to encode a single, simple concept, when in fact they are encoding something far more complex. The same effect holds for linear combinations of activations. We trace the source of this illusion to geometric properties of BERT's embedding space as well as the fact that common text corpora represent only narrow slices of possible English sentences. We provide a taxonomy of model-learned concepts and discuss methodological implications for in…
Institute of Information Systems, University of Liechtenstein（列支敦士登大学信息系统学院）；Department of Information Systems, HEC, University of Lausanne（洛桑大学高等商学院信息系统系）
We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN). It uses a decoder to transform the non-interpretable representation of the given layer to a representation that is more similar to the domain a human is familiar with. In an image recognition problem, one can recognize what information is represented by a layer by contrasting reconstructed images of \emph{ClaDec} with those of a conventional auto-encoder(AE) serving as reference. We also extend \emph{ClaDec} to allow the trade-off betw…
Causality is Key for Interpretability Claims to Generalise
Mila - Qu\'ebec AI Institute \& Universit\'e de Montr\'eal；Boston University；Cold Spring Harbor Laboratory；Max-Planck-Institute for Intelligent Systems, ELLIS Institute T\"ubingen, University of T\"ubingen
Deep neural networks (DNNs) are being increasingly used to make predictions from functional magnetic resonance imaging (fMRI) data. However, they are widely seen as uninterpretable "black boxes", as it can be difficult to discover what input information is used by the DNN in the process, something important in both cognitive neuroscience and clinical applications. A saliency map is a common approach for producing interpretable visualizations of the relative importance of input features for a prediction. However, methods for creating maps often fail due to DNNs being sensitive to input noise, o…
