Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection

Soumyajit Gupta, Sooyong Lee, Maria De-Arteaga, Matthew Lease

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

9 Cites (Scopus)

Resum

Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comments targeting different demographic groups can vary markedly across groups. In such settings, trained models can be dominated by the relationships that best fit the majority group, leading to disparate performance. We propose framing toxicity detection as multi-task learning (MTL), allowing a model to specialize on the relationships that are relevant to each demographic group while also leveraging shared properties across groups. With toxicity detection, each task corresponds to identifying toxicity against a particular demographic group. However, traditional MTL requires labels for all tasks to be present for every data point. To address this, we propose Conditional MTL (CondMTL), wherein only training examples relevant to the given demographic group are considered by the loss function. This lets us learn group specific representations in each branch which are not cross contaminated by irrelevant labels. Results on synthetic and real data show that using CondMTL improves predictive recall over various baselines in general and for the minority demographic group in particular, while having similar overall accuracy.

Idioma originalAnglès
Títol de la publicacióACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023
Lloc de publicacióNew York
EditorAssociation for Computing Machinery, Inc
Pàgines3689-3700
Nombre de pàgines12
ISBN (electrònic)9781450394161
DOIs
Estat de la publicacióPublicada - 30 d’abr. 2023
Publicat externament
Esdeveniment32nd ACM World Wide Web Conference, WWW 2023 - Austin, United States
Durada: 30 d’abr. 20234 de maig 2023

Sèrie de publicacions

NomACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023

Conferència

Conferència32nd ACM World Wide Web Conference, WWW 2023
País/TerritoriUnited States
CiutatAustin
Període30/04/234/05/23

Fingerprint

Navegar pels temes de recerca de 'Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection'. Junts formen un fingerprint únic.

Com citar-ho