Multi-graph Multi-label Learning with Dual-granularity Labeling

Zhao, Y; Wang, Y; Wang, Z; Zhang, C

Multi-graph Multi-label Learning with Dual-granularity Labeling

Zhao, Y Wang, Y Wang, Z Zhang, C

Permalink

Publisher:: ACM
Publication Type:: Conference Proceeding
Citation:: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 2327-2337
Issue Date:: 2021-08-14

Closed Access

	Filename	Description	Size
	3447548.3467339.pdf	Published version	1.61 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhao, Y
dc.contributor.author	Wang, Y
dc.contributor.author	Wang, Z
dc.contributor.author	Zhang, C https://orcid.org/0000-0001-5715-7154
dc.date	2021-08-14
dc.date.accessioned	2022-06-14T00:34:38Z
dc.date.available	2022-06-14T00:34:38Z
dc.date.issued	2021-08-14
dc.identifier.citation	Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 2327-2337
dc.identifier.isbn	978-1-4503-8332-5
dc.identifier.uri	http://hdl.handle.net/10453/158143
dc.description.abstract	Graphs are a powerful and versatile data structure that easily captures real life relationship. Multi-graph Multi-label learning (MGML) is a supervised learning task, which aims to learn a Multi-label classifier to label a set of objects of interest (e.g. image or text) with a bag-of-graphs representation. However, prior techniques on the MGML are developed based on transferring graphs into instances that does not fully utilize the structure information in the learning, and focus on learning the unseen labels only at the bag level. There is no existing work studying how to label the graphs within a bag that is of importance in many applications like image or text annotation. To bridge this gap, in this paper, we present a novel coarse and fine-grained Multi-graph Multi-label (cfMGML) learning framework which directly builds the learning model over the graphs and empowers the label prediction at both the coarse (aka. bag) level and fine-grained (aka. graph in each bag) level. In particular, given a set of labeled multi-graph bags, we design the scoring functions at both graph and bag levels to model the relevance between the label and data using specific graph kernels. Meanwhile, we propose a thresholding rank-loss objective function to rank the labels for the graphs and bags and minimize the hamming-loss simultaneously at one-step, which aims to address the error accumulation issue in traditional rank-loss algorithms. To tackle the non-convex optimization problem, we further develop an effective sub-gradient descent algorithm to handle high-dimensional space computation required in cfMGML. Experiments over various real-world datasets demonstrate cfMGML achieves superior performance than the state-of-arts algorithms.
dc.language	en
dc.publisher	ACM
dc.relation.ispartof	Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
dc.relation.ispartof	ACM Conference on Knowledge Discovery & Data Mining
dc.relation.isbasedon	10.1145/3447548.3467339
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Multi-graph Multi-label Learning with Dual-granularity Labeling
dc.type	Conference Proceeding
utslib.location.activity	Virtual Event Singapore
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/DVC (International)
pubs.organisational-group	/University of Technology Sydney/Strength - ACRI - Australia China Relations Institute
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-06-14T00:34:36Z
pubs.finish-date	2021-08-18
pubs.place-of-publication	USA
pubs.publication-status	Published
pubs.start-date	2021-08-14
dc.location	USA

Abstract:

Graphs are a powerful and versatile data structure that easily captures real life relationship. Multi-graph Multi-label learning (MGML) is a supervised learning task, which aims to learn a Multi-label classifier to label a set of objects of interest (e.g. image or text) with a bag-of-graphs representation. However, prior techniques on the MGML are developed based on transferring graphs into instances that does not fully utilize the structure information in the learning, and focus on learning the unseen labels only at the bag level. There is no existing work studying how to label the graphs within a bag that is of importance in many applications like image or text annotation. To bridge this gap, in this paper, we present a novel coarse and fine-grained Multi-graph Multi-label (cfMGML) learning framework which directly builds the learning model over the graphs and empowers the label prediction at both the coarse (aka. bag) level and fine-grained (aka. graph in each bag) level. In particular, given a set of labeled multi-graph bags, we design the scoring functions at both graph and bag levels to model the relevance between the label and data using specific graph kernels. Meanwhile, we propose a thresholding rank-loss objective function to rank the labels for the graphs and bags and minimize the hamming-loss simultaneously at one-step, which aims to address the error accumulation issue in traditional rank-loss algorithms. To tackle the non-convex optimization problem, we further develop an effective sub-gradient descent algorithm to handle high-dimensional space computation required in cfMGML. Experiments over various real-world datasets demonstrate cfMGML achieves superior performance than the state-of-arts algorithms.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/158143