Video Experimental Relacionado
Updated: Sep 9, 2025

03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
681
DA-PFL: Agregación dinámica de afinidad en el aprendizaje federado personalizado bajo desequilibrio de clase
IEEE transactions on neural networks and learning systems
|September 3, 2025
Resumen
Este estudio introduce un modelo de aprendizaje federado personalizado basado en la afinidad dinámica (PFL) para abordar el desequilibrio de clase. El nuevo enfoque mejora la precisión del modelo para clientes individuales en escenarios de aprendizaje federados.
Área de la Ciencia:
- Inteligencia artificial
- Aprendizaje automático
- Sistemas distribuidos
Sus antecedentes:
- El aprendizaje federado personalizado (PFL) tiene como objetivo crear modelos personalizados para cada cliente.
- Los métodos PFL actuales a menudo agregan clientes con distribuciones de datos similares.
- Esta agregación basada en la similitud puede empeorar el problema del desequilibrio de clase en los conjuntos de datos.
Objetivo del estudio:
- Proponer un nuevo modelo dinámico basado en la afinidad (DA-PFL).
- Para aliviar el problema de desequilibrio de clase inherente al aprendizaje federado.
- Mejorar el rendimiento de los modelos de aprendizaje personalizado.
Principales métodos:
- Desarrolló una métrica de afinidad complementaria para guiar la agregación de clientes.
- Implementó una estrategia de agregación dinámica ajustando la selección de clientes en cada ronda.
- Evaluado el modelo DA-PFL en cuatro conjuntos de datos del mundo real.
Principales resultados:
- El modelo DA-PFL mejoró significativamente la precisión del cliente.
- Redujeron efectivamente el impacto negativo del desequilibrio de clase durante el aprendizaje federado.
- Superó a los métodos de comparación más avanzados existentes.
Conclusiones:
- El modelo DA-PFL propuesto ofrece una solución eficaz para el desequilibrio de clase en PFL.
- La agregación dinámica basada en la afinidad mejora el rendimiento del modelo personalizado.
- DA-PFL demuestra una precisión superior en diversos conjuntos de datos.
Videos de Conceptos Relacionados
Aggregates Classification
380
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
380
Affinity and Avidity
36.6K
Overview
36.6K
Associative Learning
569
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
569
In- and Out-Groups
39.9K
People all belong to a gender, race, age, and social economic group. These groups provide a powerful source of our identity and self-esteem (Tajfel & Turner, 1979) and serve as our in-groups. An in-group is a group that we identify with or see ourselves as belonging to.
39.9K
Maximum Size of Aggregate
229
The maximum size of aggregate is defined as the aperture of the sieve retaining 15 percent or more of the particles present in the aggregate sample. The aggregate's maximum size impacts the concrete's water requirement, workability, and strength. Larger aggregates reduce the surface area needing cement paste coverage, which can lower water needs, thereby allowing a decrease in the water-to-cement ratio when the desired workability and richness of the mix are to be maintained, which can...
229
Law of Independent Assortment
56.5K
While Mendel’s Law of Segregation states that the two alleles for one gene are separated into different gametes, a different question of how different genes are inherited remains. For example, is the gene for tall plants inherited with the gene for green peas? Mendel asked this question by experimenting with a dihybrid cross; a cross in which both parents are homozygous for two distinct traits resulting in an F1 generation that are heterozygous for both traits.
56.5K