相关论文: Neuron to Graph: Interpreting Language Model Neuro…

Information flows by routes inside the network via mechanisms implemented in the model. These routes can be represented as graphs where nodes correspond to token representations and edges to operations inside the network. We automatically…

Graph mining is an important area in data mining and machine learning that involves extracting valuable information from graph-structured data. In recent years, significant progress has been made in this field through the development of…

One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level…

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel…

The problem of interpreting the decisions of machine learning is a well-researched and important. We are interested in a specific type of machine learning model that deals with graph data called graph neural networks. Evaluating…

Graph-based retrieval-augmented generation (Graph-based RAG) has demonstrated significant potential in enhancing Large Language Models (LLMs) with structured knowledge. However, existing methods face three critical challenges: Inaccurate…

Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving…

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN)…

Representation learning on text-attributed graphs (TAGs) has attracted significant interest due to its wide-ranging real-world applications, particularly through Graph Neural Networks (GNNs). Traditional GNN methods focus on encoding the…

Graph Neural Networks (GNNs) have emerged as the predominant method for analyzing graph-structured data. However, canonical GNNs have limited expressive power and generalization capability, thus triggering the development of more expressive…

Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a…

Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability,…

Graphs are pervasive in the real-world, such as social network analysis, bioinformatics, and knowledge graphs. Graph neural networks (GNNs) have great ability in node classification, a fundamental task on graphs. Unfortunately, conventional…

Heterogeneous graph neural networks (HGNNs) excel at capturing structural and semantic information in heterogeneous graphs (HGs), while struggling to generalize across domains and tasks. With the rapid advancement of large language models…

Transformer neural networks show promising capabilities, in particular for uses in materials analysis, design and manufacturing, including their capacity to work effectively with both human language, symbols, code, and numerical data. Here…

We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…

Large language models (LLMs) have greatly improved their capability in performing NLP tasks. However, deeper semantic understanding, contextual coherence, and more subtle reasoning are still difficult to obtain. The paper discusses…

Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain connectivities were developed to create a comprehensive road…

Input optimization methods, such as Google Deep Dream, create interpretable representations of neurons for computer vision DNNs. We propose and evaluate ways of transferring this technology to NLP. Our results suggest that gradient ascent…

Recent development of deep neural networks (DNNs) for tabular learning has largely benefited from the capability of DNNs for automatic feature interaction. However, the heterogeneity nature of tabular features makes such features relatively…