paper-with-me

홈 › Papers

Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships

2024-03-25 · CVPR 2024 1 · Rangel Daroya, Aaron Sun, Subhransu Maji

Modeling and visualizing relationships between tasks or datasets is an important step towards solving various meta-tasks such as dataset discovery, multi-tasking, and transfer learning. However, many relationships, such as containment and transferability, are naturally asymmetric and current approaches for representation and visualization (e.g., t-SNE) do not readily support this. We propose Task2Box, an approach to represent tasks using box embeddings -- axis-aligned hyperrectangles in low dimensional spaces -- that can capture asymmetric relationships between them through volumetric overlaps. We show that Task2Box accurately predicts unseen hierarchical relationships between nodes in ImageNet and iNaturalist datasets, as well as transferability between tasks in the Taskonomy benchmark. We also show that box embeddings estimated from task representations (e.g., CLIP, Task2Vec, or attribute based) can be used to predict relationships between unseen tasks more accurately than classifiers trained on the same representations, as well as handcrafted asymmetric distances (e.g., KL divergence). This suggests that low-dimensional box embeddings can effectively capture these task relationships and have the added advantage of being interpretable. We use the approach to visualize relationships among publicly available image classification datasets on popular dataset hosting platform called Hugging Face.

📄 PDF Abstract BibTeX arXiv:2403.17173

Code (1)

cvl-umass/task2box 공식 구현 pytorch

Tasks

Attributeimage-classificationImage ClassificationTransfer Learning

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

MGKAN: Predicting Asymmetric Drug-Drug Interactions via a Multimodal Graph Kolmogorov-Arnold Network

2026-02-02 · Kunyi Fan, Mengjie Chen, Longlong Li, Cunquan Qu arxiv

Predicting drug-drug interactions (DDIs) is essential for safe pharmacological treatments. Previous graph neural network (GNN) models leverage molecular structures and interaction networks but mostly rely on linear aggre…

Graph Neural Network

Enabling Asymmetric Knowledge Transfer in Multi-Task Learning with Self-Auxiliaries

2024-10-21 · Olivier Graffeuille, Yun Sing Koh, Joerg Wicker, Moritz Lehmann

Knowledge transfer in multi-task learning is typically viewed as a dichotomy; positive transfer, which improves the performance of all tasks, or negative transfer, which hinders the performance of all tasks. In this pape…

Multi-Task LearningTransfer Learning

AsyReC: A Multimodal Graph-based Framework for Spatio-Temporal Asymmetric Dyadic Relationship Classification

2025-04-07 · Wang Tang, Fethiye Irmak Dogan, Linbo Qing, Hatice Gunes

Dyadic social relationships, which refer to relationships between two individuals who know each other through repeated interactions (or not), are shaped by shared spatial and temporal experiences. Current computational m…

Graph Neural NetworkTriplet

A Convex Formulation for Learning Task Relationships in Multi-Task Learning

2012-03-15 · Yu Zhang, Dit-yan Yeung

Multi-task learning is a learning paradigm which seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this paper, we propose a regularization formulation for le…

Multi-Task Learning

Word Representations via Gaussian Embedding

2014-12-20 · Luke Vilnis, Andrew McCallum

Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty abo…