2024/07/01 by Jesus-German Ortiz-Barajas, Ortiz-Barajas, Jesus-German, Helena Gómez-Adorno +3 · 1 citation
Computer Science · #Semantic Web and Ontologies #Model-Driven Software Engineering Techniques #Advanced Database Systems and Queries
paper · pdf · doi:10.48550/arxiv.2407.01411
We present HyperLoader, a simple approach that combines different parameter-efficient fine-tuning methods in a multi-task setting. To achieve this goal, our model uses a hypernetwork to generate the weights of these modules based on the task, the transformer layer, and its position within this layer. Our method combines the benefits of multi-task learning by capturing the structure of all tasks while reducing the task interference problem by encapsulating the task-specific knowledge in the generated weights and the benefits of combining different parameter-efficient methods to outperform full-fine tuning. We provide empirical evidence that HyperLoader outperforms previous approaches in most datasets and obtains the best average performance across tasks in high-resource and low-resource scenarios.