{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T17:53:07Z","timestamp":1771523587322,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,3,27]],"date-time":"2019-03-27T00:00:00Z","timestamp":1553644800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,3,27]],"date-time":"2019-03-27T00:00:00Z","timestamp":1553644800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DBI-1458477"],"award-info":[{"award-number":["DBI-1458477"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1007\/s10618-019-00622-6","type":"journal-article","created":{"date-parts":[[2019,3,27]],"date-time":"2019-03-27T19:50:22Z","timestamp":1553716222000},"page":"995-1016","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A new class of metrics for learning on real-valued and structured data"],"prefix":"10.1007","volume":"33","author":[{"given":"Ruiyu","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Mathews","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elizabeth A.","family":"Housworth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew W.","family":"Hahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6769-0793","authenticated-orcid":false,"given":"Predrag","family":"Radivojac","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,3,27]]},"reference":[{"key":"622_CR1","first-page":"420","volume":"2001","author":"CC Aggarwal","year":"2001","unstructured":"Aggarwal CC et al (2001) On the surprising behavior of distance metrics in high dimensional space. Proc Int Conf Database Theory (ICDT) 2001:420\u2013434","journal-title":"Proc Int Conf Database Theory (ICDT)"},{"issue":"1","key":"622_CR2","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","volume":"25","author":"M Ashburner","year":"2000","unstructured":"Ashburner M et al (2000) Gene ontology: tool for the unification of biology. Nat Genet 25(1):25\u201329","journal-title":"Nat Genet"},{"issue":"Databse issue","key":"622_CR3","first-page":"D154","volume":"33","author":"A Bairoch","year":"2005","unstructured":"Bairoch A et al (2005) The universal protein resource (UniProt). Nucleic Acids Res 33(Databse issue):D154\u2013D159","journal-title":"Nucleic Acids Res"},{"key":"622_CR4","first-page":"280","volume":"2011","author":"S Baraty","year":"2011","unstructured":"Baraty S et al (2011) The impact of triangular inequality violations on medoid-based clustering. Proc Int Symp Methodol Intell Syst (ISMIS) 2011:280\u2013289","journal-title":"Proc Int Symp Methodol Intell Syst (ISMIS)"},{"key":"622_CR5","unstructured":"Bellet A et\u00a0al (2013) A survey on metric learning for feature vectors and structured data. arXiv preprint \n                    arXiv:1306.6709"},{"key":"622_CR6","first-page":"121","volume":"2009","author":"S Ben-David","year":"2009","unstructured":"Ben-David S, Ackerman M (2009) Measures of clustering quality: a working set of axioms for clustering. Adv Neural Inf Process Syst (NIPS) 2009:121\u2013128","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"key":"622_CR7","first-page":"217","volume":"1999","author":"K Beyer","year":"1999","unstructured":"Beyer K et al (1999) When is \u201cnearest neighbor\u201d meaningful? Proc Int Conf Database Theory (ICDT) 1999:217\u2013235","journal-title":"Proc Int Conf Database Theory (ICDT)"},{"key":"622_CR8","first-page":"81","volume":"2004","author":"M Bilenko","year":"2004","unstructured":"Bilenko M et al (2004) Integrating constraints and metric learning in semi-supervised clustering. Proc Int Conf Mach Learn (ICML) 2004:81\u201388","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"issue":"10","key":"622_CR9","doi-asserted-by":"publisher","first-page":"e76339","DOI":"10.1371\/journal.pone.0076339","volume":"8","author":"M Cao","year":"2013","unstructured":"Cao M et al (2013) Going the distance for protein function prediction: a new distance metric for protein interaction networks. PLoS ONE 8(10):e76339","journal-title":"PLoS ONE"},{"key":"622_CR10","unstructured":"Cardoso-Cachopo A (2007) Improving methods for single-label text categorization. Ph.D. thesis, Instituto Superior Tecnico, Universidade Tecnica de Lisboa"},{"issue":"13","key":"622_CR11","doi-asserted-by":"publisher","first-page":"i53","DOI":"10.1093\/bioinformatics\/btt228","volume":"29","author":"WT Clark","year":"2013","unstructured":"Clark WT, Radivojac P (2013) Information-theoretic evaluation of predicted ontological annotations. Bioinformatics 29(13):i53\u2013i61","journal-title":"Bioinformatics"},{"issue":"1","key":"622_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21\u201327","journal-title":"IEEE Trans Inf Theory"},{"key":"622_CR13","volume-title":"Elements of information theory","author":"TM Cover","year":"2006","unstructured":"Cover TM, Thomas JA (2006) Elements of information theory. Wiley, Hoboken"},{"key":"622_CR14","first-page":"299","volume":"2","author":"I Csisz\u00e1r","year":"1967","unstructured":"Csisz\u00e1r I (1967) Information-type measure of difference of probability distributions and indirect observations. Studia Sci Math Hungar 2:299\u2013318","journal-title":"Studia Sci Math Hungar"},{"key":"622_CR15","first-page":"604","volume":"2006","author":"MM Dalkilic","year":"2006","unstructured":"Dalkilic MM et al (2006) Using compression to identify classes of inauthentic papers. Proc SIAM Int Conf Data Min (SDM) 2006:604\u2013608","journal-title":"Proc SIAM Int Conf Data Min (SDM)"},{"key":"622_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30958-8","volume-title":"Encyclopedia of distances","author":"MM Deza","year":"2013","unstructured":"Deza MM, Deza E (2013) Encyclopedia of distances. Springer, Berlin"},{"key":"622_CR17","first-page":"147","volume":"2003","author":"C Elkan","year":"2003","unstructured":"Elkan C (2003) Using the triangle inequality to accelerate k-means. Proc Int Conf Mach Learn (ICML) 2003:147\u2013153","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"issue":"4","key":"622_CR18","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/0031-3203(92)90091-V","volume":"25","author":"L Goldfarb","year":"1992","unstructured":"Goldfarb L (1992) What is distance and why do we need the metric model for pattern learning? Pattern Recognit 25(4):431\u2013438","journal-title":"Pattern Recognit"},{"key":"622_CR19","first-page":"377","volume":"2006","author":"D Greene","year":"2006","unstructured":"Greene D, Cunningham P (2006) Practical solutions to the problem of diagonal dominance in kernel document clustering. Proc Int Conf Mach Learn (ICML) 2006:377\u2013384","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"622_CR20","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1007\/978-3-662-44848-9_33","volume":"2014","author":"M Grosshans","year":"2014","unstructured":"Grosshans M et al (2014) Joint prediction of topics in a URL hierarchy. Proc Joint Eur Conf Mach Learn Knowl Disc Databases (ECML\/PKDD) 2014:514\u2013529","journal-title":"Proc Joint Eur Conf Mach Learn Knowl Disc Databases (ECML\/PKDD)"},{"issue":"4","key":"622_CR21","doi-asserted-by":"publisher","first-page":"2386","DOI":"10.1109\/TIT.2011.2110791","volume":"57","author":"A Guntuboyina","year":"2011","unstructured":"Guntuboyina A (2011) Lower bounds for the minimax risk using $$f$$-divergences, and applications. IEEE Trans Inform Theory 57(4):2386\u20132399","journal-title":"IEEE Trans Inform Theory"},{"key":"622_CR22","first-page":"130","volume":"2010","author":"G Hamerly","year":"2010","unstructured":"Hamerly G (2010) Making k-means even faster. Proc SIAM Int Conf Data Min (SDM) 2010:130\u2013140","journal-title":"Proc SIAM Int Conf Data Min (SDM)"},{"issue":"10","key":"622_CR23","doi-asserted-by":"publisher","first-page":"6417","DOI":"10.1109\/TIT.2014.2345760","volume":"60","author":"FF Hassanzadeh","year":"2014","unstructured":"Hassanzadeh FF, Milenkovic O (2014) An axiomatic approach to constructing distances for rank comparison and aggregation. IEEE Trans Inf Theory 60(10):6417\u20136439","journal-title":"IEEE Trans Inf Theory"},{"key":"622_CR24","first-page":"506","volume":"2000","author":"A Hinneburg","year":"2000","unstructured":"Hinneburg A et al (2000) What is the nearest neighbor in high dimensional spaces? Proc Int Conf Very Large Databases (VLDB) 2000:506\u2013515","journal-title":"Proc Int Conf Very Large Databases (VLDB)"},{"issue":"11","key":"622_CR25","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1109\/T-C.1973.223640","volume":"C\u201322","author":"RA Jarvis","year":"1973","unstructured":"Jarvis RA, Patrick EA (1973) Clustering using a similarity measure based on shared nearest neighbors. IEEE Trans Comput C\u201322(11):1025\u20131034","journal-title":"IEEE Trans Comput"},{"issue":"17","key":"622_CR26","doi-asserted-by":"publisher","first-page":"i609","DOI":"10.1093\/bioinformatics\/btu472","volume":"30","author":"Y Jiang","year":"2014","unstructured":"Jiang Y et al (2014) The impact of incomplete knowledge on the evaluation of protein function prediction: a structured-output learning perspective. Bioinformatics 30(17):i609\u2013i616","journal-title":"Bioinformatics"},{"key":"622_CR27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/978-3-642-13529-3_8","volume":"2010","author":"M Kryszkiewicz","year":"2010","unstructured":"Kryszkiewicz M, Lasek P (2010) TI-DBSCAN: clustering with DBSCAN by means of the triangle inequality. Proc Int Conf Rough Sets Curr Trends Comput (RSCTC) 2010:60\u201369","journal-title":"Proc Int Conf Rough Sets Curr Trends Comput (RSCTC)"},{"key":"622_CR28","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1145\/1772690.1772749","volume":"2010","author":"R Kumar","year":"2010","unstructured":"Kumar R, Vassilvitskii S (2010) Generalized distances between rankings. Proc Int Conf World Wide Web (WWW) 2010:571\u2013580","journal-title":"Proc Int Conf World Wide Web (WWW)"},{"issue":"1","key":"622_CR29","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1214\/aos\/1193342380","volume":"1","author":"L LeCam","year":"1973","unstructured":"LeCam L (1973) Convergence of estimates under dimensionality restrictions. Ann Stat 1(1):38\u201353","journal-title":"Ann Stat"},{"issue":"12","key":"622_CR30","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1109\/TIT.2004.838101","volume":"50","author":"M Li","year":"2004","unstructured":"Li M et al (2004) The similarity metric. IEEE Trans Inf Theory 50(12):3250\u20133264","journal-title":"IEEE Trans Inf Theory"},{"key":"622_CR31","unstructured":"Lichman M (2013) UCI machine learning repository. \n                    http:\/\/archive.ics.uci.edu\/ml"},{"issue":"10","key":"622_CR32","doi-asserted-by":"publisher","first-page":"4394","DOI":"10.1109\/TIT.2006.881731","volume":"52","author":"F Liese","year":"2006","unstructured":"Liese F, Vajda I (2006) On divergences and informations in statistics and information theory. IEEE Trans Inform Theory 52(10):4394\u20134412","journal-title":"IEEE Trans Inform Theory"},{"key":"622_CR33","doi-asserted-by":"publisher","first-page":"319","DOI":"10.4064\/cm-6-1-319-327","volume":"6","author":"E Marczewski","year":"1958","unstructured":"Marczewski E, Steinhaus H (1958) On a certain distance of sets and the corresponding distance of functions. Colloq Math 6:319\u2013327","journal-title":"Colloq Math"},{"key":"622_CR34","first-page":"397","volume":"2000","author":"AW Moore","year":"2000","unstructured":"Moore AW (2000) The anchors hierarchy: using the triangle inequality to survive high dimensional data. Proc Conf Uncertain Artif Intell (UAI) 2000:397\u2013405","journal-title":"Proc Conf Uncertain Artif Intell (UAI)"},{"key":"622_CR35","first-page":"1693","volume":"2015","author":"Y Movshovitz-Attias","year":"2015","unstructured":"Movshovitz-Attias Y et al (2015) Ontological supervision for fine grained classification of street view storefronts. IEEE Conf Comput Vis Pattern Recognit (CVPR) 2015:1693\u20131702","journal-title":"IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"issue":"6","key":"622_CR36","doi-asserted-by":"publisher","first-page":"e1002073","DOI":"10.1371\/journal.pcbi.1002073","volume":"7","author":"NL Nehrt","year":"2011","unstructured":"Nehrt NL et al (2011) Testing the ortholog conjecture with comparative functional genomic data from mammals. PLoS Comput Biol 7(6):e1002073","journal-title":"PLoS Comput Biol"},{"key":"622_CR37","doi-asserted-by":"crossref","unstructured":"Pang B, Lee L (2004) A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the annual meeting on association for computational linguistics (ACL) 2004","DOI":"10.3115\/1218955.1218990"},{"key":"622_CR38","unstructured":"Pinsker MS (1964) Information and information stability of random variables and processes. Holden-Day"},{"issue":"4","key":"622_CR39","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1287\/moor.27.4.792.304","volume":"27","author":"ST Rachev","year":"2002","unstructured":"Rachev ST, R\u00f6misch W (2002) Quantitative stability in stochastic programming: the method of probability metrics. Math Oper Res 27(4):792\u2013818","journal-title":"Math Oper Res"},{"key":"622_CR40","first-page":"2487","volume":"11","author":"M Radovanovi\u0107","year":"2010","unstructured":"Radovanovi\u0107 M et al (2010) Hubs in space: popular nearest neighbors in high-dimensional data. J Mach Learn Res 11:2487\u20132531","journal-title":"J Mach Learn Res"},{"key":"622_CR41","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316436","volume-title":"Linear statistical inference and its applications","author":"CR Rao","year":"1973","unstructured":"Rao CR (1973) Linear statistical inference and its applications, vol 2. Wiley, Hoboken"},{"issue":"1","key":"622_CR42","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/0040-5809(82)90004-1","volume":"21","author":"CR Rao","year":"1982","unstructured":"Rao CR (1982) Diversity and dissimilarity coefficients: a unified approach. Theor Popul Biol 21(1):24\u201343","journal-title":"Theor Popul Biol"},{"key":"622_CR43","doi-asserted-by":"publisher","DOI":"10.1201\/b10967","volume-title":"Introduction to bio-ontologies","author":"PN Robinson","year":"2011","unstructured":"Robinson PN, Bauer S (2011) Introduction to bio-ontologies. CRC Press, Boca Raton"},{"issue":"9","key":"622_CR44","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1093\/bioinformatics\/btp122","volume":"25","author":"MF Rogers","year":"2009","unstructured":"Rogers MF, Ben-Hur A (2009) The use of gene ontology evidence codes in preventing classifier assessment bias. Bioinformatics 25(9):1173\u20131177","journal-title":"Bioinformatics"},{"key":"622_CR45","first-page":"301","volume":"2000","author":"B Sch\u00f6lkopf","year":"2000","unstructured":"Sch\u00f6lkopf B (2000) The kernel trick for distances. Adv Neural Inf Process Syst (NIPS) 2000:301\u2013307","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"key":"622_CR46","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682","volume-title":"Kernel methods for pattern analysis","author":"J Shawe-Taylor","year":"2004","unstructured":"Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge"},{"key":"622_CR47","volume-title":"Introduction to data mining","author":"PN Tan","year":"2006","unstructured":"Tan PN et al (2006) Introduction to data mining. Pearson, New York"},{"key":"622_CR48","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1145\/2939672.2939779","volume":"2016","author":"KM Ting","year":"2016","unstructured":"Ting KM et al (2016) Overcoming key weaknesses of distance-based neighbourhood methods using a data dependent dissimilarity measure. Proc Int Conf Knowl Discov Data Min (KDD) 2016:1205\u20131214","journal-title":"Proc Int Conf Knowl Discov Data Min (KDD)"},{"key":"622_CR49","first-page":"207","volume":"10","author":"KQ Weinberger","year":"2009","unstructured":"Weinberger KQ, Saul LK (2009) Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 10:207\u2013244","journal-title":"J Mach Learn Res"},{"issue":"3","key":"622_CR50","doi-asserted-by":"publisher","first-page":"e18011","DOI":"10.1371\/journal.pone.0018011","volume":"6","author":"D Wu","year":"2011","unstructured":"Wu D et al (2011) Stalking the fourth domain in metagenomic data: searching for, discovering, and interpreting novel, deep branches in marker gene phylogenetic trees. PLoS ONE 6(3):e18011","journal-title":"PLoS ONE"},{"key":"622_CR51","doi-asserted-by":"publisher","DOI":"10.1201\/9781420089653","volume-title":"The top ten algorithms in data mining","author":"X Wu","year":"2009","unstructured":"Wu X, Kumar V (2009) The top ten algorithms in data mining. CRC Press, Boca Raton"},{"key":"622_CR52","first-page":"521","volume":"2003","author":"EP Xing","year":"2003","unstructured":"Xing EP et al (2003) Distance metric learning with application to clustering with side-information. Adv Neural Inf Process Syst (NIPS) 2003:521\u2013528","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"issue":"2","key":"622_CR53","first-page":"4","volume":"2","author":"L Yang","year":"2006","unstructured":"Yang L, Jin R (2006) Distance metric learning: a comprehensive survey. Mich State Univ 2(2):4","journal-title":"Mich State Univ"},{"issue":"6","key":"622_CR54","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/TPAMI.2007.1078","volume":"29","author":"L Yujian","year":"2007","unstructured":"Yujian L, Bo L (2007) A normalized Levenshtein distance metric. IEEE Trans Pattern Anal Mach Intell 29(6):1091\u20131095","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"622_CR55","first-page":"264","volume":"28","author":"VM Zolotarev","year":"1983","unstructured":"Zolotarev VM (1983) Probability metrics. Teor Veroyatnost i Primenen 28(2):264\u2013287","journal-title":"Teor Veroyatnost i Primenen"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-019-00622-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10618-019-00622-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-019-00622-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T13:53:48Z","timestamp":1589723628000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10618-019-00622-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,27]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["622"],"URL":"https:\/\/doi.org\/10.1007\/s10618-019-00622-6","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,27]]},"assertion":[{"value":"11 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}