Deep learning models have shown great performances in natural language processing tasks. While much attention has been paid to improvements in utility, privacy leakage and social bias are two major concerns arising in trained models. In order to tackle these problems, we protect individuals' sensitive information and mitigate gender bias simultaneously. First, we propose a selective privacy-preserving method that only obscures individuals' sensitive information. Then we propose a negative multi-task learning framework to mitigate the gender bias which contains a main task and a gender prediction task. We analyze two existing word embeddings and evaluate them on sentiment analysis and a medical text classification task. Our experimental results show that our negative multi-task learning framework can mitigate the gender bias while keeping models’ utility.
Deep learning models have shown their great performances in natural language processing tasks. While much attention has been paid towards improvements in utility, privacy leakage and social bias are two major concerns arising in trained models. In this paper, we protect individual privacy and mitigate gender bias on classification models simultaneously. First, we propose a selective privacy-preserving method that only obscure individuals' sensitive information by adding noise on word embeddings. Then we propose a negative multi-task learning framework to mitigate the gender bias which contains a main task and a gender prediction task. The main task uses a positive loss constraint to ensure utility while the gender prediction task applies a negative loss constraint to remove gender-specific features. We analyze two existing word embeddings and evaluate them on sentiment analysis and medical text classification tasks. Our experimental results show that our negative multi-task learning framework can mitigate the gender bias while keeping models’ utility on both sentiment analysis and medical text classification.
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Transcription factors (TFs) play a fundamental role in gene regulation by selectively binding to specific DNA sequences. Understanding the nature and behavior of these TFs is essential for insights into gene regulation dynamics. In this study, we introduce a robust multi-task learning framework specifically tailored to harness both TF-specific annotations and TF-related domain annotations, thereby enhancing the accuracy of TF predictions. Notably, we incorporate cutting-edge language models that have recently garnered attention for their outstanding performance across various fields, particularly in biological computations like protein sequence modeling. Comparative experimental analysis with existing models, DeepTFactor and TFpredict, reveals that our multi-task learning framework achieves an accuracy exceeding 92% across four evaluation metrics on the TF prediction task, surpassing both competitors. Our work marks a significant leap in the domain of TF prediction, enriching our comprehension of gene regulatory mechanisms and paving the way for the discovery of novel regulatory motifs.
Cerebral cavernous malformations (CCMs) are abnormal expansions of brain capillaries that increase the risk of hemorrhagic strokes, with CCM1 mutations responsible for about 50% of familial cases. The disorder can cause irreversible brain damage by compromising the blood–brain barrier (BBB), leading to fatal brain hemorrhages. Studies show that progesterone and its derivatives significantly impact BBB integrity. The three CCM proteins (CCM1, CCM2, and CCM3) form the CCM signaling complex (CSC), linking classic and non-classic progesterone signaling within the CmPn network, which is crucial for maintaining BBB integrity. This study aimed to explore the relationship between CCM1 and key pathways of the CmPn signaling network using three mouse embryonic fibroblast lines (MEFs) with distinct CCM1 expressions. Omics and systems biology analysis investigated CCM1-mediated signaling within the CmPn network. Our findings reveal that CCM1 is essential for regulating cellular processes within progesterone-mediated CmPn/CmP signaling, playing a crucial role in maintaining microvessel integrity. This regulation occurs partly through gene transcription control. The critical role of CCM1 in these processes suggests it could be a promising therapeutic target for CCMs.