File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.knosys.2019.105155
- Scopus: eid_2-s2.0-85075460455
- WOS: WOS:000517663200002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Geometric Knowledge Embedding for unsupervised domain adaptation
Title | Geometric Knowledge Embedding for unsupervised domain adaptation |
---|---|
Authors | |
Keywords | Domain adaptation Graph-based model Geometric knowledge Graph convolutional network Maximum Mean Discrepancy |
Issue Date | 2020 |
Publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/knosys |
Citation | Knowledge-Based Systems, 2020, v. 191, p. article no. 105155 How to Cite? |
Abstract | Domain adaptation aims to transfer auxiliary knowledge from a source domain to enhance the learning performance on a target domain. Recent studies have suggested that deep networks are able to achieve promising results for domain adaptation problems. However, deep neural networks cannot reveal the underlying geometric information from input data. Indeed, such geometric information is very useful for describing the relationship between the samples from source and target domains. In this paper, we propose a novel learning algorithm named GKE, which stands for Geometric Knowledge Embedding. In GKE, we use a graph-based model to explore the underlying geometric structure of the input source and target data based on their similarities. Concretely, we develop a graph convolutional network to learn discriminative representations based on the constructed graph. To obtain effective transferable representations, we match source and target domains by reducing the Maximum Mean Discrepancy (MMD) between their learned representations. Extensive experiments on real-world data sets demonstrate that the proposed method outperforms existing domain adaption methods. |
Persistent Identifier | http://hdl.handle.net/10722/287957 |
ISSN | 2023 Impact Factor: 7.2 2023 SCImago Journal Rankings: 2.219 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wu, H | - |
dc.contributor.author | Yan, Y | - |
dc.contributor.author | Ye, Y | - |
dc.contributor.author | Ng, MK | - |
dc.contributor.author | Wu, Q | - |
dc.date.accessioned | 2020-10-05T12:05:44Z | - |
dc.date.available | 2020-10-05T12:05:44Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Knowledge-Based Systems, 2020, v. 191, p. article no. 105155 | - |
dc.identifier.issn | 0950-7051 | - |
dc.identifier.uri | http://hdl.handle.net/10722/287957 | - |
dc.description.abstract | Domain adaptation aims to transfer auxiliary knowledge from a source domain to enhance the learning performance on a target domain. Recent studies have suggested that deep networks are able to achieve promising results for domain adaptation problems. However, deep neural networks cannot reveal the underlying geometric information from input data. Indeed, such geometric information is very useful for describing the relationship between the samples from source and target domains. In this paper, we propose a novel learning algorithm named GKE, which stands for Geometric Knowledge Embedding. In GKE, we use a graph-based model to explore the underlying geometric structure of the input source and target data based on their similarities. Concretely, we develop a graph convolutional network to learn discriminative representations based on the constructed graph. To obtain effective transferable representations, we match source and target domains by reducing the Maximum Mean Discrepancy (MMD) between their learned representations. Extensive experiments on real-world data sets demonstrate that the proposed method outperforms existing domain adaption methods. | - |
dc.language | eng | - |
dc.publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/knosys | - |
dc.relation.ispartof | Knowledge-Based Systems | - |
dc.subject | Domain adaptation | - |
dc.subject | Graph-based model | - |
dc.subject | Geometric knowledge | - |
dc.subject | Graph convolutional network | - |
dc.subject | Maximum Mean Discrepancy | - |
dc.title | Geometric Knowledge Embedding for unsupervised domain adaptation | - |
dc.type | Article | - |
dc.identifier.email | Ng, MK: michael.ng@hku.hk | - |
dc.identifier.authority | Ng, MK=rp02578 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.knosys.2019.105155 | - |
dc.identifier.scopus | eid_2-s2.0-85075460455 | - |
dc.identifier.hkuros | 315734 | - |
dc.identifier.volume | 191 | - |
dc.identifier.spage | article no. 105155 | - |
dc.identifier.epage | article no. 105155 | - |
dc.identifier.isi | WOS:000517663200002 | - |
dc.publisher.place | Netherlands | - |
dc.identifier.issnl | 0950-7051 | - |