Visualizing Coalition Formation: From Hedonic Games to Image Segmentation
This work provides a visual diagnostic testbed for coalition formation in hedonic games, offering insights into how mechanism design parameters impact equilibrium structures for multi-agent systems researchers.
This paper models image segmentation as a hedonic game to visualize coalition formation, studying how a granularization parameter affects equilibrium fragmentation and boundary structure. On the Weizmann benchmark, they observe transitions from cohesive to fragmented but recoverable equilibria, and finally to intrinsic failure under excessive fragmentation.
We propose image segmentation as a visual diagnostic testbed for coalition formation in hedonic games. Modeling pixels as agents on a graph, we study how a granularization parameter shapes equilibrium fragmentation and boundary structure. On the Weizmann single-object benchmark, we relate multi-coalition equilibria to binary protocols by measuring whether the converged coalitions overlap with a foreground ground-truth. We observe transitions from cohesive to fragmented yet recoverable equilibria, and finally to intrinsic failure under excessive fragmentation. Our core contribution links multi-agent systems with image segmentation by quantifying the impact of mechanism design parameters on equilibrium structures.