{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T07:06:50Z","timestamp":1746860810594,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/bigdata.2016.7840869","type":"proceedings-article","created":{"date-parts":[[2017,2,7]],"date-time":"2017-02-07T21:46:59Z","timestamp":1486504019000},"page":"2363-2367","source":"Crossref","is-referenced-by-count":2,"title":["Implementing dictionary learning in Apache Flink, Or: How I learned to relax and love iterations"],"prefix":"10.1109","author":[{"given":"Geoffrey","family":"Mon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milad","family":"Makkie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shannon","family":"Quinn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"10","article-title":"Discretized streams: an efficient and fault-tolerant model for stream processing on large clusters","author":"zaharia","year":"2012","journal-title":"Proceedings of the 4th USENIX Conference on Hot Topics in Cloud Ccomputing USENIX Association"},{"key":"ref11","article-title":"Flink vs. Spark","author":"baltagi","year":"2015","journal-title":"Flink Forward"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-014-0357-y"},{"journal-title":"Flink Scalable Batch and Stream Data Processing","article-title":"Apache Software Foundation","year":"2016","key":"ref13"},{"key":"ref14","first-page":"28","article-title":"Apache Flink: Stream and batch processing in a single engine","volume":"38","author":"carbone","year":"2015","journal-title":"Bulletin of the IEEE Computer Society Technical Committee on Data Engineering"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7841533"},{"journal-title":"Apache Software Foundation Apache Flink 1 1 3 documentation Concepts","year":"0","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350245"},{"journal-title":"Python interface for new API (Map\/Reduce)","year":"0","author":"schepler","key":"ref18"},{"journal-title":"Rework operator distribution","year":"0","author":"schepler","key":"ref19"},{"key":"ref4","first-page":"10","article-title":"Spark: cluster computing with working sets","volume":"10","author":"zaharia","year":"2010","journal-title":"HotCloud"},{"key":"ref3","first-page":"513","article-title":"Iterative non-linear dimensionality reduction with manifold sculpting","volume":"8","author":"gashler","year":"2007","journal-title":"NIPS"},{"journal-title":"Apache spark - lightning-fast cluster computing","article-title":"Apache Software Foundation","year":"2016","key":"ref6"},{"key":"ref5","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation USENIX Association"},{"key":"ref8","first-page":"599","article-title":"GraphX: Graph processing in a distributed dataflow framework","author":"gonzalez","year":"2014","journal-title":"11 th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14778\/2831360.2831365"},{"key":"ref2","first-page":"66","article-title":"Dimensionality reduction: a comparative","volume":"10","author":"van","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"1","article-title":"MLlib: Machine learning in Apache Spark","volume":"17","author":"meng","year":"2016","journal-title":"JMLR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300015990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939730"},{"key":"ref22","first-page":"801","article-title":"Efficient sparse coding algorithms","author":"lee","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2014.2369495"},{"journal-title":"Add Aggregation support to Python API","year":"0","author":"mon","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2015.04.002"},{"journal-title":"Use Apache Flink on Amazon EMR","year":"0","author":"foster","key":"ref26"},{"journal-title":"zipWithIndex in Python API","year":"0","author":"quinn","key":"ref25"}],"event":{"name":"2016 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2016,12,5]]},"location":"Washington DC,USA","end":{"date-parts":[[2016,12,8]]}},"container-title":["2016 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7818133\/7840573\/07840869.pdf?arnumber=7840869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T22:24:46Z","timestamp":1488407086000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7840869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2016.7840869","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}