Today’s data driven systems and official statistics often oversimplify the concept of gender, reducing it to binary data, with far-reaching implications for policy development and equitable access to services. This simplification can lead to misclassification and discrimination against individuals who identify as non-binary. We are working to advance our research in this area to develop new, more equitable approaches that can avoid discrimination based on gender identity. Within this research framework, our primary focus is on mitigating the problem of underrepresentation and, in some cases, the complete absence of non-binary individuals in data collection. With this goal in mind, we present the GINN Gender InclusioNeural Network. This is our first attempt to develop an equitable neural network that accurately identifies gender in a multiclass context and includes individuals whose gender identity does not fall on the binary spectrum. To achieve this goal, we conducted a comprehensive comparative analysis of several finetuned neural network models. Our goal was to gain a deep understanding of the crucial distinguishing features in gender identify classification and to highlight the limitation of current methods using explainable AI techniques. The initial results are promising and demonstrate the effectiveness of a fine-tuned EfficientNetB0 model in accurately categorizing images of individuals into their self-reported gender, but we are skeptical about the application in a real-world scenario because of the amount of data available about non-binary people at the moment.
GINN: Towards Gender InclusioNeural Network / Berta, M.; Vacchetti, B.; Cerquitelli, T.. - (2023), pp. 4119-4126. (Intervento presentato al convegno 2023 IEEE International Conference on Big Data (BigData) tenutosi a Sorrento (IT) nel 15-18 december 2023) [10.1109/BigData59044.2023.10386328].
GINN: Towards Gender InclusioNeural Network
Vacchetti B.;Cerquitelli T.
2023
Abstract
Today’s data driven systems and official statistics often oversimplify the concept of gender, reducing it to binary data, with far-reaching implications for policy development and equitable access to services. This simplification can lead to misclassification and discrimination against individuals who identify as non-binary. We are working to advance our research in this area to develop new, more equitable approaches that can avoid discrimination based on gender identity. Within this research framework, our primary focus is on mitigating the problem of underrepresentation and, in some cases, the complete absence of non-binary individuals in data collection. With this goal in mind, we present the GINN Gender InclusioNeural Network. This is our first attempt to develop an equitable neural network that accurately identifies gender in a multiclass context and includes individuals whose gender identity does not fall on the binary spectrum. To achieve this goal, we conducted a comprehensive comparative analysis of several finetuned neural network models. Our goal was to gain a deep understanding of the crucial distinguishing features in gender identify classification and to highlight the limitation of current methods using explainable AI techniques. The initial results are promising and demonstrate the effectiveness of a fine-tuned EfficientNetB0 model in accurately categorizing images of individuals into their self-reported gender, but we are skeptical about the application in a real-world scenario because of the amount of data available about non-binary people at the moment.File | Dimensione | Formato | |
---|---|---|---|
GINN__Gender_InclusioNeural_Network.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
10.21 MB
Formato
Adobe PDF
|
10.21 MB | Adobe PDF | Visualizza/Apri |
GINN_Towards_Gender_InclusioNeural_Network.pdf
non disponibili
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
10.26 MB
Formato
Adobe PDF
|
10.26 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2987325