Collaborative AI service dataset enables complex AI workflows integration
A Collaborative Artificial Intelligence as a Service Composition Dataset
Computer Science and Game Theory
Summary
Combining multiple AI services to solve complex problems is a growing area, but it needs good examples and tools to study how these services work together. The authors created a large dataset that describes many AI services and requests for combining them into bigger solutions. They also developed a method to test which combinations of AI services are likely to work well before actually connecting them. This makes it easier to research and build systems that use many AI tools working together.
What this means in practice
- •For cloud platform engineers: Create and evaluate complex AI workflows that combine multiple providers’ services using realistic data and benchmarks.
- •For ai service developers: Develop smarter algorithms to recommend and select the best AI services for collaborative compositions before deployment.
Authors
Deepak Kanneganti, Sajib Mistry, Sheik Fattah, Aneesh Krishna
Abstract
Artificial Intelligence as a Service (AIaaS) composition is an emerging research area that enables clients to combine multiple AI services to meet complex requirements. A recent extension of this paradigm is collaborative AIaaS composition, where multiple AI services are combined to create a unified solution. Research in this field requires datasets with service descriptions, composition requests, and corresponding composition solutions. However, no dataset contains all this information specifically for collaborative AIaaS composition. Existing datasets target traditional web services or sequential AI workflows and lack the AI-specific attributes required for realistic collaborative composition. To address these challenges, we present a collaborative AIaaS composition dataset containing 25,900 AIaaS services from multiple providers across 12 AI task families, along with 10,000 collaborative service requests. We further develop a Multi-Armed Bandit (MAB)-based collaborative composition algorithm that determines the composability of candidate service combinations prior to composition. Experimental results demonstrate that the dataset supports realistic collaborative AIaaS composition evaluation and related research in service recommendation, selection and QoS prediction. The dataset and implementation are publicly available at: https://github.com/deepakkanneganti9/CAIaaS