hypervolume-based optimization

Fixed-weight-vector approaches in MOEA/D suffer from poor convergence and uneven solution distribution when handling irregular Pareto fronts—e.g., degenerate, discontinuous, or inverted fronts. Method: This paper proposes an indicator-driven adaptive weight vector optimization algorithm, integrating the MOEA/D decomposition framework with a simplified hypervolume (S-HV) indicator. Under guidance from the R2 indicator, the algorithm dynamically adjusts the frequency of weight vector updates to enable real-time improvement of solution distribution. Contribution/Results: The key innovation lies in deeply embedding indicator-based evaluation into the weight vector evolution process, thereby jointly optimizing convergence and diversity. Experimental results on 12 irregular benchmark problems demonstrate that the proposed algorithm significantly outperforms six state-of-the-art multi-objective evolutionary algorithms, exhibiting superior robustness and search efficiency—particularly on complex front geometries.

To address incomplete Pareto front coverage and difficulties in high-dimensional ray sampling in multi-objective optimization (MOO), this paper proposes PHN-HVVS: a novel framework that replaces conventional ray-based sampling with a Voronoi mesh-driven spatial partitioning strategy. It integrates hypernetwork modeling with genetic algorithm optimization and introduces an hypervolume (HV)-guided loss function to significantly improve front coverage and convexity adaptability. The method incorporates a multi-objective cooperative federated learning architecture. Empirical evaluation on multiple MOO benchmarks demonstrates substantial improvements in Pareto set quality—measured by HV, IGD, and other standard metrics—over state-of-the-art methods. Furthermore, PHN-HVVS is validated in a collaborative federated learning setting, where it effectively balances model personalization and global fairness.

High-dimensional solution sets generated by multi-objective evolutionary algorithms (MOEAs) pose significant challenges for analysis and interpretation. Method: This paper proposes a modular, algorithm-agnostic interactive visual analytics framework specifically designed for evolutionary multi-objective optimization (EMO) solution sets. It introduces the first explainable visual analytics paradigm for EMO, integrating dynamic Pareto front encoding, coordinated multi-view interaction, user-driven focus-context mechanisms, adaptive dimensionality reduction, and real-time Pareto dominance computation. Implemented using WebGL/Canvas and D3.js/React, the framework supports joint exploration of decision and objective spaces. Contribution/Results: Expert evaluation and case studies demonstrate that the framework substantially improves efficiency in identifying solution set distribution patterns and deepens understanding of trade-off relationships, enabling reproducible, interactive, and interpretable analysis of MOEA outcomes.

In offline multi-objective optimization (MOO), generative models struggle to effectively leverage design-label data and approximate high-quality Pareto fronts. Method: This paper proposes a flow-matching-based generative optimization framework that integrates three novel components: multi-objective weighted prediction guidance, local Pareto filtering, and neighborhood distribution evolution sampling—enabling uniform coverage of the weight space and cross-distribution knowledge transfer. Unlike single-objective guidance paradigms, our framework directly models the conditional generation flow over the Pareto front, enhancing both sampling directionality and diversity. Results: Evaluated on multiple benchmark tasks, the method significantly improves the coverage, convergence, and uniformity of the Pareto solution set. State-of-the-art performance demonstrates its effectiveness and generalizability across diverse MOO settings.

The R2 indicator for bi-objective optimization lacks strict Pareto compatibility—i.e., adding a dominated solution may not increase the indicator value. Method: This paper proposes an analytical variant of R2 based on a continuous uniform Tchebycheff utility function. We theoretically prove that this continuous R2 exhibits strict Pareto compatibility for bi-objective problems: adding any non-dominated solution strictly increases the indicator, and adding any dominated solution necessarily increases it. We further devise an exact O(N log N) algorithm, enabling the first efficient and theoretically compliant unary quality assessment. Results: Experiments show that the proposed indicator achieves evaluation performance comparable to hypervolume (HV), yet with significantly higher computational efficiency. It thus fills a critical gap in bi-objective set-quality indicators by simultaneously offering rigorous theoretical guarantees and practical scalability.

This work addresses a critical gap in multi-objective optimization: the absence of a finite-set quality indicator that simultaneously guarantees strict Pareto compliance and effectively evaluates boundary points. The study introduces, for the first time, the concept of “magnitude” from metric geometry to construct a novel scalar indicator that is strictly Pareto compliant. By integrating coordinate projection with magnitude theory from category theory, the proposed metric exhibits both weak and strict set monotonicity and positively identifies boundary solutions—addressing key limitations of the hypervolume indicator. The associated algorithm achieves Θ(n log n) time complexity in two and three dimensions. Empirical results demonstrate that magnitude favors populations containing boundary points and complete Das–Dennis reference grids, whereas hypervolume tends to prefer densely filled interior configurations.

This work addresses a critical gap in preference-guided expected improvement criteria for multi-objective Bayesian optimization: the lack of a systematic understanding of the interplay among geometric structure, monotonicity, and exact computation. By analytically examining the geometric nature of hypervolume and the R2 indicator in both objective and scalarized spaces, the study reveals that the R2-based expected improvement corresponds to a volume in scalarized space rather than a weighted hypervolume in objective space. Building on this insight, the authors unify various hypervolume variants under a common computational perspective and introduce two exact calculation approaches—an ER2I algorithm based on finite summation for discrete settings and an integral-based method leveraging Gaussian surrogate models. Furthermore, they establish an achievement scalarizing optimization framework grounded in scalar Gaussian expected improvement and rigorously analyze its Pareto compliance and monotonicity properties.

This work addresses the challenges of convergence in multi-objective optimization arising from non-differentiable objective functions and abrupt structural changes in nondominated fronts. To this end, the authors propose a nonsmooth set-based gradient ascent method that uniquely integrates an amplitude indicator with a hierarchical weighting scheme. They derive its exact gradient and prove its computational complexity is equivalent to that of hypervolume gradient computation. By employing hierarchical aggregation, the method establishes a connection to infinitesimal coding, thereby elucidating the underlying mechanics of nonsmooth optimization. The algorithm further incorporates projected finite differences, repulsion and stagnation-recovery strategies, and coordinate-projected geometric expansion techniques. Experimental results on standard two- and three-objective benchmarks, as well as curved and hyperspherical Pareto fronts, demonstrate that the proposed approach efficiently and robustly approximates the Pareto front.

This study addresses the impact of objective scale disparity on the definition and approximation of regions of interest (ROIs) in preference-driven evolutionary multi-objective optimization. It systematically investigates whether ROIs should be defined in the normalized or original objective space, conducting comparative experiments using an evolutionary algorithm that incorporates estimates of both ideal and extreme points. The work reveals, for the first time, the fundamental reason why ROIs defined in normalized space are inherently difficult to approximate accurately. It demonstrates that defining ROIs in the original objective space yields significantly better approximation quality, particularly when objective scales are heterogeneous. These findings provide a theoretical foundation and practical guidance for selecting the appropriate objective space in preference-guided optimization frameworks.

This work addresses the challenge of out-of-distribution (OOD) data in offline multi-objective optimization, which often leads surrogate models to generate unrealistic and overly extreme Pareto solutions. To mitigate this issue, the authors propose DOMOO, a novel approach that incorporates cumulative risk control to alleviate OOD effects, jointly optimizes preference and Pareto parameters through nested Pareto set learning, and employs a diversity-driven selection strategy to enhance both solution quality and uniformity. The study also introduces IGD_offline, an innovative evaluation metric tailored for offline settings that balances convergence and diversity. Extensive experiments demonstrate that DOMOO achieves the best average ranking across multiple synthetic and real-world benchmarks, significantly outperforming existing methods.