في هذا العمل، نعتبر مشكلة تصميم أطر تعليمية آمنة وفعالة (FLF) ل NLP.الحلول القائمة تحت هذه الأدبيات إما النظر في مجمع موثوق أو تتطلب بدائريات تشفير ثقيلة الوزن، مما يجعل الأداء يتدهور بشكل كبير.علاوة على ذلك، تعمل العديد من تصاميم FL FL Secure الموجودة فقط بموجب الافتراض التقييدي الذي يمكن إسقاط أي منهما من بروتوكول التدريب.لمعالجة هذه المشكلات، نقترح SEFL، وهو إطار تعليمي آمن وفعال في الفيدروس (1) يلغي الحاجة إلى الكيانات الموثوق بها؛(2) يحقق دقة نموذجية مماثلة وحتى أفضل مقارنة بتصميمات فلوريدا الحالية؛(3) مرن للتسربين العميل.
In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks for NLP. Existing solutions under this literature either consider a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded. Moreover, many existing secure FL designs work only under the restrictive assumption that none of the clients can be dropped out from the training protocol. To tackle these problems, we propose SEFL, a secure and efficient federated learning framework that (1) eliminates the need for the trusted entities; (2) achieves similar and even better model accuracy compared with existing FL designs; (3) is resilient to client dropouts.
References used
https://aclanthology.org/
News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users' historical news click behavior data, which may lead to privacy concerns and hazards. Federated Learning is a
Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to leverage
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying fast-emergin
To build machine learning-based applications for sensitive domains like medical, legal, etc. where the digitized text contains private information, anonymization of text is required for preserving privacy. Sequence tagging, e.g. as done in Named Enti