Global-Order GFlowNets
This addresses a specific problem in multi-objective optimization for researchers and practitioners, representing an incremental improvement over existing GFlowNet methods.
The paper tackles the limitation of Order-Preserving GFlowNets, where local ordering causes conflicting optimization objectives in multi-objective black-box optimization, by introducing Global-Order GFlowNets that transform local order into global order to resolve these conflicts, with experimental evaluations showing efficacy and promise.
Order-Preserving (OP) GFlowNets have demonstrated remarkable success in tackling complex multi-objective (MOO) black-box optimization problems using stochastic optimization techniques. Specifically, they can be trained online to efficiently sample diverse candidates near the Pareto front. A key advantage of OP GFlowNets is their ability to impose a local order on training samples based on Pareto dominance, eliminating the need for scalarization - a common requirement in other approaches like Preference-Conditional GFlowNets. However, we identify an important limitation of OP GFlowNets: imposing a local order on training samples can lead to conflicting optimization objectives. To address this issue, we introduce Global-Order GFlowNets, which transform the local order into a global one, thereby resolving these conflicts. Our experimental evaluations on various benchmarks demonstrate the efficacy and promise of our proposed method.