Cross-Modal Similarity Learning via Pairs, Preferences, and Active Supervision
Lists
Only you see this
Abstract
We present a probabilistic framework for learning pair-wise similarities between objects belonging to different modalities, such as drugs and proteins, or text and images. Our framework is based on learning a binary code based representation for objects in each modality, and has the following key properties: (i) it can leverage both pairwise as well as easy-to-obtain relative preference based cross-modal constraints, (ii) the probabilistic framework naturally allows querying for the most useful/informative constraints, facilitating an active learning setting (existing methods for cross-modal similarity learning do not have such a mechanism), and (iii) the binary code length is learned from the data. We demonstrate the effectiveness of the proposed approach on two problems that require computing pairwise similarities between cross-modal object pairs: cross-modal link prediction in bipartite graphs, and hashing based cross-modal similarity search.
BibTeX
@inproceedings{zhen2015cross,
author = {Yi Zhen and Piyush Rai and Hongyuan Zha and Lawrence Carin},
title = {{Cross-Modal Similarity Learning via Pairs, Preferences, and Active Supervision}},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2015},
doi = {10.1609/aaai.v29i1.9599},
}