An attention model for the formation of collectives in real-world domains
This addresses the problem of efficiently forming collectives for applications aligned with Sustainable Development Goals, such as shared mobility and cooperative learning, but it is incremental as it builds on existing methods.
The paper tackles the problem of forming collectives of agents for real-world applications like ridesharing and cooperative learning by proposing a general approach combining an attention model and an integer linear program. Results show it provides solutions comparable to domain-specific state-of-the-art methods and outperforms a recent general approach based on Monte Carlo tree search.
We consider the problem of forming collectives of agents for real-world applications aligned with Sustainable Development Goals (e.g., shared mobility, cooperative learning). We propose a general approach for the formation of collectives based on a novel combination of an attention model and an integer linear program (ILP). In more detail, we propose an attention encoder-decoder model that transforms a collective formation instance to a weighted set packing problem, which is then solved by an ILP. Results on two real-world domains (i.e., ridesharing and team formation for cooperative learning) show that our approach provides solutions that are comparable (in terms of quality) to the ones produced by state-of-the-art approaches specific to each domain. Moreover, our solution outperforms the most recent general approach for forming collectives based on Monte Carlo tree search.