Hyperbolic Personalized Tag Recommendation

Abstract

Visual analytics supports data analysis tasks within complex domain problems. However, due to the richness of data types, visual designs, and interaction designs, users need to recall and process a significant amount of information when they visually analyze data. These challenges emphasize the need for more intelligent visual analytics methods. Large language models have demonstrated the ability to interpret various forms of textual data, offering the potential to facilitate intelligent support for visual analytics. We propose LEVA, a framework that uses large language models to enhance users' VA workflows at multiple stages: onboarding, exploration, and summarization. To support onboarding, we use large language models to interpret visualization designs and view relationships based on system specifications. For exploration, we use large language models to recommend insights based on the analysis of system status and data to facilitate mixed-initiative exploration. For summarization, we present a selective reporting strategy to retrace analysis history through a stream visualization and generate insight reports with the help of large language models. We demonstrate how LEVA can be integrated into existing visual analytics systems. Two usage scenarios and a user study suggest that LEVA effectively aids users in conducting visual analytics.

Joint Modeling of Citation Networks and User Preferences for Academic Tagging Recommender System

“…Techniques such as hierarchical attention models and graph neural networks integrate collaboration signals and generate richer entity representations [24]. Additionally, some works explore different vector spaces to learn entity representations and measure semantic correlations [25], such as using hyperbolic spaces and tangent space optimization [26]. To directly capture the interactions between users, items, and tags, methods like the Tag-aware Attentional Graph Neural Network (TA-GNN) [7] and variational self-encoders [8] have been proposed, which utilize attention mechanisms and metric learning to understand better and leverage these interactions [9].…”

A Graph Neural Networks-Based Learning Framework With Hyperbolic Embedding for Personalized Tag Recommendation

“…To exploit mutual semantic relationships among users/items for collaborative filtering tasks, [35] introduced a neighbor construction strategy to build user and item semantic neighborhoods and developed a deep framework with hyperbolic geometry to integrate constructed neighborhoods into the recommendation. Regarding personalized tag recommendation, [37] proposed HPTR to learn the tagging information in hyperbolic space and utilize hyperbolic distance to model the entities' interactions.…”

“…• ABNT: ABNT [6] utilizes the multi-layer perception to model nonlinear interactions between users, items, and tag, and employs attention networks to capture complex patterns of users' behaviors. • HPTR: HPTR [37] learns the representations of entities by modeling their interactive relationships in hyperbolic space and utilizes hyperbolic distance to measure semantic relevance between entities. • GNN-PTR: GNN-PTR [8] is a graph-neural-networks enhanced tag recommendation model, which introduce the GNN to the pairwise interaction tensor factorization framework for mining high-order similarity between embeddings.…”