Related papers: Automated Circuit Interpretation via Probe Prompti…

Pre-trained protein models (PTPMs) represent a protein with one fixed embedding and thus are not capable for diverse tasks. For example, protein structures can shift, namely protein folding, between several conformations in various…

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes…

It is well acknowledged that incorporating explicit knowledge graphs (KGs) can benefit question answering. Existing approaches typically follow a grounding-reasoning pipeline in which entity nodes are first grounded for the query (question…

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…

We present a quantitative circuit-level analysis of diffusion models, establishing computational pathways and mechanistic principles underlying image generation processes. Through systematic intervention experiments across 2,000 synthetic…

Mechanistic interpretability aims to reverse engineer the computation performed by a neural network in terms of its internal components. Although there is a growing body of research on mechanistic interpretation of neural networks, the…

We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by…

In this paper, we propose PLACE (Prompt Learning for Attributed Community Search), an innovative graph prompt learning framework for ACS. Enlightened by prompt-tuning in Natural Language Processing (NLP), where learnable prompt tokens are…

Explainable artificial intelligence (XAI) is an important area in the AI community, and interpretability is crucial for building robust and trustworthy AI models. While previous work has explored model-level and instance-level explainable…

Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explainability method. However, recent research has exposed the…

Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs which provides faithful explanations by design. L2XGNN…

Mechanistic interpretability has transformed the analysis of transformer circuits by decomposing model behavior into competing algorithms, identifying phase transitions during training, and deriving closed-form predictions for when and why…

Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. However, there has been little work on interpreting them, and specifically on understanding which parts of the graphs…

Molecular property prediction is essential in a variety of contemporary scientific fields, such as drug development and designing energy storage materials. Although there are many machine learning models available for this purpose, those…

Graph neural networks (GNNs) have shown great potential in learning on graphs, but they are known to perform sub-optimally on link prediction tasks. Existing GNNs are primarily designed to learn node-wise representations and usually fail to…

Learning from complex real-life networks is a lively research area, with recent advances in learning information-rich, low-dimensional network node representations. However, state-of-the-art methods are not necessarily interpretable and are…

Transformer-based language models are treated as black-boxes because of their large number of parameters and complex internal interactions, which is a serious safety concern. Mechanistic Interpretability (MI) intends to reverse-engineer…

Deep neural networks (DNNs) have demonstrated remarkable performance across various domains, but their inherent complexity makes them challenging to interpret. This is especially true for temporal graph regression tasks due to the complex…

Retrieval-Augmented Generation (RAG) has become a robust framework for enhancing Large Language Models (LLMs) with external knowledge. Recent advances in RAG have investigated graph based retrieval for intricate reasoning; however, the…

Recent research has demonstrated the efficacy of pre-training graph neural networks (GNNs) to capture the transferable graph semantics and enhance the performance of various downstream tasks. However, the semantic knowledge learned from…