FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989596816> ?p ?o ?g. }

• W2989596816 abstract "This work addresses a new problem that learns generative adversarial networks (GANs) from multiple data collections that are each i) owned separately by different clients and ii) drawn from a non-identical distribution that comprises different classes. Given such non-iid data as input, we aim to learn a distribution involving all the classes input data can belong to, while keeping the data decentralized in each client storage. Our key contribution to this end is a new decentralized approach for learning GANs from non-iid data called Forgiver-First Update (F2U), which a) asks clients to train an individual discriminator with their own data and b) updates a generator to fool the most `forgiving' discriminators who deem generated samples as the most real. Our theoretical analysis proves that this updating strategy allows the decentralized GAN to achieve a generator's distribution with all the input classes as its global optimum based on f-divergence minimization. Moreover, we propose a relaxed version of F2U called Forgiver-First Aggregation (F2A) that performs well in practice, which adaptively aggregates the discriminators while emphasizing forgiving ones. Our empirical evaluations with image generation tasks demonstrated the effectiveness of our approach over state-of-the-art decentralized learning methods." @default.
• W2989596816 created "2019-12-05" @default.
• W2989596816 creator A5020282208 @default.
• W2989596816 creator A5026581043 @default.
• W2989596816 creator A5038408644 @default.
• W2989596816 creator A5077707500 @default.
• W2989596816 date "2019-05-23" @default.
• W2989596816 modified "2023-09-27" @default.
• W2989596816 title "Decentralized Learning of Generative Adversarial Networks from Non-iid Data" @default.
• W2989596816 cites W1665214252 @default.
• W2989596816 cites W1836465849 @default.
• W2989596816 cites W1921523184 @default.
• W2989596816 cites W2066537788 @default.
• W2989596816 cites W2099471712 @default.
• W2989596816 cites W2117539524 @default.
• W2989596816 cites W2125389028 @default.
• W2989596816 cites W2194775991 @default.
• W2989596816 cites W2405756170 @default.
• W2989596816 cites W2520464687 @default.
• W2989596816 cites W2524365899 @default.
• W2989596816 cites W2535838896 @default.
• W2989596816 cites W2548275288 @default.
• W2989596816 cites W2554506842 @default.
• W2989596816 cites W2593116425 @default.
• W2989596816 cites W2593414223 @default.
• W2989596816 cites W2599354622 @default.
• W2989596816 cites W2750384547 @default.
• W2989596816 cites W2767079719 @default.
• W2989596816 cites W2793925626 @default.
• W2989596816 cites W2810065831 @default.
• W2989596816 cites W2895171208 @default.
• W2989596816 cites W2899730059 @default.
• W2989596816 cites W2903471046 @default.
• W2989596816 cites W2949987290 @default.
• W2989596816 cites W2951934944 @default.
• W2989596816 cites W2962754210 @default.
• W2989596816 cites W2962793481 @default.
• W2989596816 cites W2962879692 @default.
• W2989596816 cites W2962900302 @default.
• W2989596816 cites W2962928367 @default.
• W2989596816 cites W2963073614 @default.
• W2989596816 cites W2963228337 @default.
• W2989596816 cites W2963684088 @default.
• W2989596816 cites W2963706720 @default.
• W2989596816 cites W2963712608 @default.
• W2989596816 cites W2963767194 @default.
• W2989596816 cites W2963784072 @default.
• W2989596816 cites W2963803379 @default.
• W2989596816 cites W2963836885 @default.
• W2989596816 cites W2963873275 @default.
• W2989596816 cites W2963981733 @default.
• W2989596816 cites W2964004663 @default.
• W2989596816 cites W2964121744 @default.
• W2989596816 cites W2972087877 @default.
• W2989596816 cites W3038028469 @default.
• W2989596816 hasPublicationYear "2019" @default.
• W2989596816 type Work @default.
• W2989596816 sameAs 2989596816 @default.
• W2989596816 citedByCount "7" @default.
• W2989596816 countsByYear W29895968162019 @default.
• W2989596816 countsByYear W29895968162020 @default.
• W2989596816 countsByYear W29895968162021 @default.
• W2989596816 crossrefType "posted-content" @default.
• W2989596816 hasAuthorship W2989596816A5020282208 @default.
• W2989596816 hasAuthorship W2989596816A5026581043 @default.
• W2989596816 hasAuthorship W2989596816A5038408644 @default.
• W2989596816 hasAuthorship W2989596816A5077707500 @default.
• W2989596816 hasConcept C11413529 @default.
• W2989596816 hasConcept C119857082 @default.
• W2989596816 hasConcept C121332964 @default.
• W2989596816 hasConcept C124101348 @default.
• W2989596816 hasConcept C138885662 @default.
• W2989596816 hasConcept C147764199 @default.
• W2989596816 hasConcept C154945302 @default.
• W2989596816 hasConcept C163258240 @default.
• W2989596816 hasConcept C199360897 @default.
• W2989596816 hasConcept C207390915 @default.
• W2989596816 hasConcept C26517878 @default.
• W2989596816 hasConcept C2777212361 @default.
• W2989596816 hasConcept C2779803651 @default.
• W2989596816 hasConcept C2780992000 @default.
• W2989596816 hasConcept C37736160 @default.
• W2989596816 hasConcept C38652104 @default.
• W2989596816 hasConcept C39890363 @default.
• W2989596816 hasConcept C41008148 @default.
• W2989596816 hasConcept C41895202 @default.
• W2989596816 hasConcept C48103436 @default.
• W2989596816 hasConcept C62520636 @default.
• W2989596816 hasConcept C76155785 @default.
• W2989596816 hasConcept C94915269 @default.
• W2989596816 hasConceptScore W2989596816C11413529 @default.
• W2989596816 hasConceptScore W2989596816C119857082 @default.
• W2989596816 hasConceptScore W2989596816C121332964 @default.
• W2989596816 hasConceptScore W2989596816C124101348 @default.
• W2989596816 hasConceptScore W2989596816C138885662 @default.
• W2989596816 hasConceptScore W2989596816C147764199 @default.
• W2989596816 hasConceptScore W2989596816C154945302 @default.
• W2989596816 hasConceptScore W2989596816C163258240 @default.
• W2989596816 hasConceptScore W2989596816C199360897 @default.
• W2989596816 hasConceptScore W2989596816C207390915 @default.

• next