In this position paper we discuss the problem of exploiting data provenance to provide explanations in data-centric AI processes, where the emphasis of model development is placed on the quality of data. In particular, we show how a classification of the main operators used in the data preparation phase provides an effective and powerful means for the production of increasingly detailed explanations at the needed level of data granularity.
Missier, P., Torlone, R. (2024). From why-provenance to why+provenance: Towards addressing deep data explanations in Data-Centric AI. In CEUR Workshop Proceedings (pp.508-517). CEUR-WS.
From why-provenance to why+provenance: Towards addressing deep data explanations in Data-Centric AI
Missier P.;Torlone R.
2024-01-01
Abstract
In this position paper we discuss the problem of exploiting data provenance to provide explanations in data-centric AI processes, where the emphasis of model development is placed on the quality of data. In particular, we show how a classification of the main operators used in the data preparation phase provides an effective and powerful means for the production of increasingly detailed explanations at the needed level of data granularity.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
