Adaptively learning the crowd kernel
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
We introduce an algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen triplet-based relative-similarity queries. Each query has the form "is object a more similar to b or to c?" and is chosen to be maximally informative given the preceding responses. The output is an embedding of the objects into Euclidean space (like MDS); we refer to this as the "crowd kernel." SVMs reveal that the crowd kernel captures prominent and subtle features across a number of domains, such as "is striped" among neckties and "vowel vs. consonant" among letters.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Proceedings of the 28th International Conference on Machine Learning, ICML 2011 |
Sider (fra-til) | 673-680 |
Antal sider | 8 |
Status | Udgivet - 2011 |
Eksternt udgivet | Ja |
Begivenhed | 28th International Conference on Machine Learning, ICML 2011 - Bellevue, WA, USA Varighed: 28 jun. 2011 → 2 jul. 2011 |
Konference
Konference | 28th International Conference on Machine Learning, ICML 2011 |
---|---|
Land | USA |
By | Bellevue, WA |
Periode | 28/06/2011 → 02/07/2011 |
Sponsor | Amazon.com, Inc. (Biz), NSF, Microsoft, Google, Yahoo! Labs |
ID: 301831017