FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037308981> ?p ?o ?g. }

• W3037308981 abstract "Current machine learning algorithms are designed to work with huge volumes of high dimensional data such as images. However, these algorithms are being increasingly deployed to resource constrained systems such as mobile devices and embedded systems. Even in cases where large computing infrastructure is available, the size of each data instance, as well as datasets, can provide a huge bottleneck in data transfer across communication channels. Also, there is a huge incentive both in energy and monetary terms in reducing both the computational and memory requirements of these algorithms. For non-parametric models that require to leverage the stored training data at the inference time, the increased cost in memory and computation could be even more problematic. In this work, we aim to reduce the volume of data these algorithms must process through an end-to-end two-stage neural subset selection model, where the first stage selects a set of candidate points using a conditionally independent Bernoulli mask followed by an iterative coreset selection via a conditional Categorical distribution. The subset selection model is trained by meta-learning with a distribution of sets. We validate our method on set reconstruction and classification tasks with feature selection as well as the selection of representative samples from a given dataset, on which our method outperforms relevant baselines. We also show in our experiments that our method enhances scalability of non-parametric models such as Neural Processes." @default.
• W3037308981 created "2020-07-02" @default.
• W3037308981 creator A5032342509 @default.
• W3037308981 creator A5039532323 @default.
• W3037308981 creator A5070302452 @default.
• W3037308981 creator A5074644698 @default.
• W3037308981 creator A5086698569 @default.
• W3037308981 date "2020-06-25" @default.
• W3037308981 modified "2023-09-27" @default.
• W3037308981 title "Stochastic Subset Selection." @default.
• W3037308981 cites W1834627138 @default.
• W3037308981 cites W1912128066 @default.
• W3037308981 cites W2108598243 @default.
• W3037308981 cites W2229366996 @default.
• W3037308981 cites W2404724429 @default.
• W3037308981 cites W2412589713 @default.
• W3037308981 cites W2432717477 @default.
• W3037308981 cites W2547875792 @default.
• W3037308981 cites W2560609797 @default.
• W3037308981 cites W2563408008 @default.
• W3037308981 cites W2601450892 @default.
• W3037308981 cites W2604392022 @default.
• W3037308981 cites W2616159609 @default.
• W3037308981 cites W2626778328 @default.
• W3037308981 cites W2786502346 @default.
• W3037308981 cites W2794302998 @default.
• W3037308981 cites W2804602357 @default.
• W3037308981 cites W2891867110 @default.
• W3037308981 cites W2894384847 @default.
• W3037308981 cites W2901100112 @default.
• W3037308981 cites W2902302021 @default.
• W3037308981 cites W2910612230 @default.
• W3037308981 cites W2913375711 @default.
• W3037308981 cites W2920448302 @default.
• W3037308981 cites W2944551240 @default.
• W3037308981 cites W2951004968 @default.
• W3037308981 cites W2952165242 @default.
• W3037308981 cites W2952433032 @default.
• W3037308981 cites W2952689920 @default.
• W3037308981 cites W2954732411 @default.
• W3037308981 cites W2963094037 @default.
• W3037308981 cites W2963121255 @default.
• W3037308981 cites W2963149687 @default.
• W3037308981 cites W2963365341 @default.
• W3037308981 cites W2963902936 @default.
• W3037308981 cites W2963981733 @default.
• W3037308981 cites W2964010828 @default.
• W3037308981 cites W2966132576 @default.
• W3037308981 cites W3037590790 @default.
• W3037308981 cites W92634156 @default.
• W3037308981 hasPublicationYear "2020" @default.
• W3037308981 type Work @default.
• W3037308981 sameAs 3037308981 @default.
• W3037308981 citedByCount "0" @default.
• W3037308981 crossrefType "posted-content" @default.
• W3037308981 hasAuthorship W3037308981A5032342509 @default.
• W3037308981 hasAuthorship W3037308981A5039532323 @default.
• W3037308981 hasAuthorship W3037308981A5070302452 @default.
• W3037308981 hasAuthorship W3037308981A5074644698 @default.
• W3037308981 hasAuthorship W3037308981A5086698569 @default.
• W3037308981 hasConcept C119857082 @default.
• W3037308981 hasConcept C124101348 @default.
• W3037308981 hasConcept C148483581 @default.
• W3037308981 hasConcept C149635348 @default.
• W3037308981 hasConcept C153083717 @default.
• W3037308981 hasConcept C154945302 @default.
• W3037308981 hasConcept C2776214188 @default.
• W3037308981 hasConcept C2780513914 @default.
• W3037308981 hasConcept C41008148 @default.
• W3037308981 hasConcept C48044578 @default.
• W3037308981 hasConcept C77088390 @default.
• W3037308981 hasConcept C81917197 @default.
• W3037308981 hasConceptScore W3037308981C119857082 @default.
• W3037308981 hasConceptScore W3037308981C124101348 @default.
• W3037308981 hasConceptScore W3037308981C148483581 @default.
• W3037308981 hasConceptScore W3037308981C149635348 @default.
• W3037308981 hasConceptScore W3037308981C153083717 @default.
• W3037308981 hasConceptScore W3037308981C154945302 @default.
• W3037308981 hasConceptScore W3037308981C2776214188 @default.
• W3037308981 hasConceptScore W3037308981C2780513914 @default.
• W3037308981 hasConceptScore W3037308981C41008148 @default.
• W3037308981 hasConceptScore W3037308981C48044578 @default.
• W3037308981 hasConceptScore W3037308981C77088390 @default.
• W3037308981 hasConceptScore W3037308981C81917197 @default.
• W3037308981 hasLocation W30373089811 @default.
• W3037308981 hasOpenAccess W3037308981 @default.
• W3037308981 hasPrimaryLocation W30373089811 @default.
• W3037308981 hasRelatedWork W1631476648 @default.
• W3037308981 hasRelatedWork W2175173358 @default.
• W3037308981 hasRelatedWork W2587314205 @default.
• W3037308981 hasRelatedWork W2615180724 @default.
• W3037308981 hasRelatedWork W2616526340 @default.
• W3037308981 hasRelatedWork W2771135177 @default.
• W3037308981 hasRelatedWork W2778459472 @default.
• W3037308981 hasRelatedWork W2787209145 @default.
• W3037308981 hasRelatedWork W2787332259 @default.
• W3037308981 hasRelatedWork W2889473071 @default.
• W3037308981 hasRelatedWork W2905417435 @default.
• W3037308981 hasRelatedWork W2914797641 @default.
• W3037308981 hasRelatedWork W2946423597 @default.

• next