Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01HMNDS02YP3EKDC9EEB3B0175> ?p ?o. }
Showing items 1 to 33 of
33
with 100 items per page.
- 01HMNDS02YP3EKDC9EEB3B0175 classification C1.
- 01HMNDS02YP3EKDC9EEB3B0175 date "2023".
- 01HMNDS02YP3EKDC9EEB3B0175 language "eng".
- 01HMNDS02YP3EKDC9EEB3B0175 type conference.
- 01HMNDS02YP3EKDC9EEB3B0175 hasPart 01J2B33XAMXVA05HDK36FDWB33.pdf.
- 01HMNDS02YP3EKDC9EEB3B0175 subject "Mathematics and Statistics".
- 01HMNDS02YP3EKDC9EEB3B0175 doi "10.1007/978-3-031-40837-3_2".
- 01HMNDS02YP3EKDC9EEB3B0175 isbn "9783031408366".
- 01HMNDS02YP3EKDC9EEB3B0175 isbn "9783031408373".
- 01HMNDS02YP3EKDC9EEB3B0175 issn "0302-9743".
- 01HMNDS02YP3EKDC9EEB3B0175 issn "1611-3349".
- 01HMNDS02YP3EKDC9EEB3B0175 presentedAt urn:uuid:830ee46c-1516-496d-8ea7-08d4ab11b42a.
- 01HMNDS02YP3EKDC9EEB3B0175 volume "14065".
- 01HMNDS02YP3EKDC9EEB3B0175 abstract "Asymmetric Shapley values (ASVs) are an extension of Shapley values that allow a user to incorporate partial causal knowledge into the explanation process. Unfortunately, computing ASVs requires sampling permutations, which quickly becomes computationally expensive. We propose A-PDD-SHAP, an algorithm that employs a functional decomposition approach to approximate ASVs at a speed orders of magnitude faster compared to permutation sampling, which significantly reduces the amortized complexity of computing ASVs when many explanations are needed. Apart from this, once the A-PDD-SHAP model is trained, it can be used to compute both symmetric and asymmetric Shapley values without having to re-train or re-sample, allowing for very efficient comparisons between different types of explanations.".
- 01HMNDS02YP3EKDC9EEB3B0175 author E8A6CF80-087D-11E4-827A-32ED4B2F559A.
- 01HMNDS02YP3EKDC9EEB3B0175 author F6172C18-F0ED-11E1-A9DE-61C894A0A6B4.
- 01HMNDS02YP3EKDC9EEB3B0175 author urn:uuid:1f884d10-a9ec-4fb2-aa86-4c71765f9c67.
- 01HMNDS02YP3EKDC9EEB3B0175 author urn:uuid:eabb4aac-e84c-454c-973d-e804623feea6.
- 01HMNDS02YP3EKDC9EEB3B0175 dateCreated "2024-01-21T07:11:50Z".
- 01HMNDS02YP3EKDC9EEB3B0175 dateModified "2024-11-28T00:09:18Z".
- 01HMNDS02YP3EKDC9EEB3B0175 editor urn:uuid:14a0f2aa-6760-4527-8b9f-499a0381b142.
- 01HMNDS02YP3EKDC9EEB3B0175 editor urn:uuid:2375e440-6ae3-46ad-8591-69479ceac43c.
- 01HMNDS02YP3EKDC9EEB3B0175 editor urn:uuid:2a92e021-68cb-4582-a2b9-a73bdbc03ff1.
- 01HMNDS02YP3EKDC9EEB3B0175 editor urn:uuid:9502c1a8-d547-4244-a68f-a94263b094be.
- 01HMNDS02YP3EKDC9EEB3B0175 editor urn:uuid:b8da48ee-2422-4007-8476-37fe052db69b.
- 01HMNDS02YP3EKDC9EEB3B0175 editor urn:uuid:bff89f02-97fb-472e-964c-4490135f2715.
- 01HMNDS02YP3EKDC9EEB3B0175 name "Efficient approximation of asymmetric Shapley values using functional decomposition".
- 01HMNDS02YP3EKDC9EEB3B0175 pagination urn:uuid:777be8e7-2d23-4a50-a35f-2cf05ecbbff4.
- 01HMNDS02YP3EKDC9EEB3B0175 publisher urn:uuid:c8eca73e-b4fb-4386-9155-0a7c49ad8879.
- 01HMNDS02YP3EKDC9EEB3B0175 sameAs LU-01HMNDS02YP3EKDC9EEB3B0175.
- 01HMNDS02YP3EKDC9EEB3B0175 sourceOrganization urn:uuid:4471712a-33df-44df-bc9a-108076516251.
- 01HMNDS02YP3EKDC9EEB3B0175 sourceOrganization urn:uuid:da897e71-8337-437a-8f2e-e757c47775ea.
- 01HMNDS02YP3EKDC9EEB3B0175 type C1.