面向文本与多媒体数据的高效图及基于秩的上下文嵌入
Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data
浏览论文内容
中文总结 AI 辅助
本研究提出无监督框架GRaCE，通过基于秩的度量生成可解释嵌入，在文本、图像等多数据集的检索、分类、聚类任务中优于RaDE及原始特征。
中文摘要 AI 辅助
在数据驱动的世界中，高效组织与映射对象间的关系至关重要。图是建模此类关联的强大工具，已广泛应用于社交网络、电信及生物学领域。然而，基于图的方法常面临高计算成本问题，尤其在内存与空间使用方面。为解决这一问题，图嵌入技术（又称网络表示学习）将图信息编码为低维表示，同时保留结构特征。但传统方法缺乏可解释的维度。RaDE（秩扩散嵌入）引入了一种基于秩信息的新方法，其关键步骤是选择代表性节点子集，以实现维度的可解释性并提升检索任务性能。尽管RaDE具有潜力，但其原始方案未充分探索不同类别下代表性子集选择的有效性，也未在分类、聚类等任务中评估嵌入效果。受RaDE启发，本研究提出GRaCE（基于图与秩的上下文嵌入），这是一种完全无监督的框架，通过利用鲁棒的基于秩的度量进行代表性子集选择与节点嵌入，生成可解释的嵌入。在文本及图像集合等不同数据集上，GRaCE在检索、分类、聚类任务中的表现均优于RaDE及原始特征；本研究以最先进的Transformer模型作为特征描述符，以图卷积网络模型作为分类任务模型开展实验。
英文摘要
In a data-driven world, efficiently organizing and mapping relationships between objects is crucial. Graphs are powerful tools for modeling these connections, being widely used in social networks, telecommunications, and biology. However, graph-based methods often face high computational costs, particularly in memory and space usage. To address this, graph embedding techniques, also referred to as Network Representation Learning, encode graph information into lower-dimensional representations while preserving structural aspects. Traditional methods, however, lack interpretable dimensions. RaDE (Rank Diffusion Embedding) introduces a new approach using rank-based information, with a key step being the selection of a representative subset of nodes to provide interpretability for its dimensions and improve retrieval tasks. Despite its potential, RaDE's original proposal did not fully explore the effectiveness of representative subset selection across different classes or evaluate embeddings in tasks like classification and clustering. Inspired by RaDE, this work introduces GRaCE (Graph and Rank-based Contextual Embeddings), a fully unsupervised framework that generates interpretable embeddings by leveraging robust rank-based measures for representative subset selection and node embedding. GRaCE surpasses RaDE and Original Features across diverse datasets, including textual and image collections, excelling in retrieval, classification, and clustering tasks, considering state-of-the-art Transformer models as feature descriptors and Graph Convolutional Networks models in classification tasks.
发表机构
- State University of São Paulo (UNESP)（圣保罗州立大学（UNESP））
- University of São Paulo (USP)（圣保罗大学（USP））
- University of Manchester（曼彻斯特大学）
- Idiap Research Institute（Idiap研究所）
机构由 AI 辅助整理，请以论文原文为准。
