Search papers, labs, and topics across Lattice.
This paper introduces DB-GEN, a decoupled basis-vector-driven generative framework for dynamic multi-objective optimization that tackles challenges like non-linear coupling, negative transfer, and cold starts. DB-GEN uses discrete wavelet transform to decouple dynamic modes, sparse dictionary learning to learn transferable basis vectors, and a surrogate-assisted search to sample initial populations. Evaluated on dynamic benchmarks, DB-GEN achieves improved tracking accuracy with zero-shot generation in milliseconds, outperforming existing algorithms.
Achieve millisecond-speed zero-shot tracking of Pareto fronts in dynamic multi-objective optimization by decoupling dynamic modes and learning transferable basis vectors.
Dynamic multi-objective optimization requires continuous tracking of moving Pareto fronts. Existing methods struggle with irregular mutations and data sparsity, primarily facing three challenges: the non-linear coupling of dynamic modes, negative transfer from outdated historical data, and the cold-start problem during environmental switches. To address these issues, this paper proposes a decoupled basis-vector-driven generative framework (DB-GEN). First, to resolve non-linear coupling, the framework employs the discrete wavelet transform to separate evolutionary trajectories into low-frequency trends and high-frequency details. Second, to mitigate negative transfer, it learns transferable basis vectors via sparse dictionary learning rather than directly memorizing historical instances. Recomposing these bases under a topology-aware contrastive constraint constructs a structured latent manifold. Finally, to overcome the cold-start problem, a surrogate-assisted search paradigm samples initial populations from this manifold. Pre-trained on 120 million solutions, DB-GEN performs direct online inference without retraining or fine-tuning. This zero-shot generation process executes in milliseconds, requiring approximately 0.2 seconds per environmental change. Experimental results demonstrate that DB-GEN improves tracking accuracy across various dynamic benchmarks compared to existing algorithms.
