arXiv:2511.14073v2 Announce Type: replace 
Abstract: Multi-label sentiment classification plays a vital role in natural language processing by detecting multiple emotions within a single text. However, existing datasets like GoEmotions often suffer from severe class imbalance, which hampers model performance, especially for underrepresented emotions. To address this, we constructed a balanced multi-label sentiment dataset by integrating the original GoEmotions data, emotion-labeled samples from Sentiment140 using a RoBERTa-base-GoEmotions model, and manually annotated texts generated by GPT-4 mini. Our data balancing strategy ensured an even distribution across 28 emotion categories. Based on this dataset, we developed an enhanced multi-label classification model that combines pre-trained FastText embeddings, convolutional layers for local feature extraction, bidirectional LSTM for contextual learning, and an attention mechanism to highlight sentiment-relevant words. A sigmoid-activated output layer enables multi-label prediction, and mixed precision training improves computational efficiency. Experimental results demonstrate significant improvements in accuracy, precision, recall, F1-score, and AUC compared to models trained on imbalanced data, highlighting the effectiveness of our approach.

تتركز هذه الدراسة على تحسين تصنيف المشاعر متعدد التسميات، وهو أمر حيوي في معالجة اللغة الطبيعية للكشف عن مشاعر متعددة داخل نص واحد. تسلط الضوء على مشكلة عدم التوازن في الفئات في مجموعات البيانات مثل GoEmotions، مما يؤثر على أداء النموذج. لمعالجة ذلك، تم إنشاء مجموعة بيانات متوازنة من خلال دمج بيانات GoEmotions الأصلية مع عينات موسومة بالعواطف من Sentiment140 ونصوص تم إنشاؤها بواسطة GPT-4. تم تطوير نموذج تصنيف محسّن باستخدام تقنيات متقدمة، بما في ذلك تضمينات FastText وآليات الانتباه.

El estudio se centra en mejorar la clasificación de sentimientos multi-etiqueta, crucial en el procesamiento del lenguaje natural para identificar diversas emociones en el texto. Destaca el problema del desequilibrio de clases en conjuntos de datos como GoEmotions, que afecta el rendimiento del modelo. Para abordar esto, se creó un conjunto de datos equilibrado al fusionar GoEmotions con muestras etiquetadas emocionalmente de Sentiment140 y textos generados por GPT-4. Se desarrolló un modelo de clasificación mejorado utilizando técnicas avanzadas, incluidos embeddings de FastText y mecanismos …

Cette étude se concentre sur l'amélioration de la classification des sentiments multi-étiquettes, essentielle dans le traitement du langage naturel pour identifier diverses émotions dans le texte. Elle souligne le problème du déséquilibre des classes dans des ensembles de données comme GoEmotions, qui affecte les performances des modèles. Pour y remédier, un ensemble de données équilibré a été créé en fusionnant GoEmotions avec des échantillons étiquetés émotionnellement de Sentiment140 et des textes générés par GPT-4. Un modèle de classification amélioré a été développé en utilisant des techn…

The study focuses on enhancing multi-label sentiment classification, crucial in natural language processing for identifying various emotions in text. It highlights the issue of class imbalance in datasets like GoEmotions, which affects model performance. To combat this, a balanced dataset was created by merging GoEmotions with emotion-labeled samples from Sentiment140 and texts generated by GPT-4. An improved classification model was developed using advanced techniques, including FastText embeddings and attention mechanisms.

Based on Data Balancing and Model Improvement for Multi-Label Sentiment Classification Performance Enhancement

arXiv:2503.04971v2 Announce Type: replace 
Abstract: Foundation models (FMs) such as GPT-4 exhibit exceptional generative capabilities across diverse downstream tasks through fine-tuning. Split Federated Learning (SFL) facilitates privacy-preserving FM fine-tuning on resource-constrained local devices by offloading partial FM computations to edge servers, enabling device-edge synergistic fine-tuning. Practical edge networks often host multiple SFL tenants to support diversified downstream tasks. However, existing research primarily focuses on single-tenant SFL scenarios, and lacks tailored incentive mechanisms for multi-tenant settings, which are essential to effectively coordinate self-interested local devices for participation in various downstream tasks, ensuring that each SFL tenant's distinct FM fine-tuning requirements (e.g., FM types, performance targets, and fine-tuning deadlines) are met. To address this gap, we propose a novel Price-Incentive Mechanism (PRINCE) that guides multiple SFL tenants to offer strategic price incentives, which solicit high-quality device participation for efficient FM fine-tuning. Specifically, we first develop a bias-resilient global SFL model aggregation scheme to eliminate model biases caused by independent device participation. We then derive a rigorous SFL convergence bound to evaluate the contributions of heterogeneous devices to FM performance improvements, guiding the incentive strategies of SFL tenants. Furthermore, we model inter-tenant device competition as a congestion game for Stackelberg equilibrium (SE) analysis, deriving each SFL tenant's optimal incentive strategy. Extensive simulations involving four representative SFL tenant types (ViT, BERT, Whisper, and LLaMA) across diverse data modalities (text, images, and audio) demonstrate that PRINCE accelerates FM fine-tuning by up to 3.07x compared to state-of-the-art approaches, while consistently meeting fine-tuning performance targets.

تم اقتراح آلية جديدة للتسعير والتحفيز (PRINCE) لتحسين التعلم الفيدرالي متعدد المستأجرين (SFL) لنماذج الأساس (FMs) مثل GPT-4، مما يتيح ضبطًا فعالًا على الأجهزة ذات الموارد المحدودة مع الحفاظ على الخصوصية. تعالج هذه الآلية تحديات التنسيق التي تواجه عدة مستأجرين في SFL لديهم احتياجات ضبط متنوعة.

Se ha propuesto un nuevo Mecanismo de Precio-Incentivo (PRINCE) para mejorar el Aprendizaje Federado de Múltiples Inquilinos (SFL) para Modelos de Fundación (FMs) como GPT-4, permitiendo un ajuste eficiente en dispositivos con recursos limitados mientras se mantiene la privacidad. Este mecanismo aborda los desafíos de coordinación que enfrentan múltiples inquilinos de SFL con diversas necesidades de ajuste.

Un nouveau mécanisme de prix incitatif (PRINCE) a été proposé pour améliorer l'apprentissage fédéré à plusieurs locataires (SFL) pour les modèles de fondation (FMs) tels que GPT-4, permettant un ajustement efficace sur des appareils à ressources limitées tout en préservant la vie privée. Ce mécanisme répond aux défis de coordination rencontrés par plusieurs locataires SFL ayant des besoins d'ajustement divers.

A novel Price-Incentive Mechanism (PRINCE) has been proposed to enhance Multi-Tenant Split Federated Learning (SFL) for Foundation Models (FMs) like GPT-4, enabling efficient fine-tuning on resource-constrained devices while maintaining privacy. This mechanism addresses the coordination challenges faced by multiple SFL tenants with diverse fine-tuning needs.

Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge

One More Thing in AI – Your Shortcut to AI Mastery

Based on Data Balancing and Model Improvement for Multi-Label Sentiment Classification Performance Enhancement

Was this article worth reading? Share it

One More Thing in AI

finlight.me

Airparser

Zemith-3bda3b

Sellm

Meteoria

Ready to build your own newsroom?