Min Jiang

Contribution. Introduces transfer learning for dynamic multiobjective optimization, so search can reuse prior environments.

Why read it. This paper opened an entire research direction — transfer learning for evolutionary dynamic optimization — and is the most-cited work in the field. Reading it gives you the foundational framework that most later algorithms build on.

Contribution. Defines evolutionary transfer optimization as a field and gives it a shared agenda.

Why read it. If your research touches transfer learning, surrogate modeling, multi-task optimization, or expensive black-box problems, this IEEE CIM article is the canonical starting point and the source most authors cite to motivate their work.

Contribution. Uses knee-point-aware transfer to avoid negative transfer when fronts shift unevenly.

Why read it. A clean diagnosis of when transfer learning helps versus hurts, plus a principled fix. It is the standard reference when arguing for selective rather than unconditional transfer in evolutionary optimization.

Contribution. Transfers solutions through learned manifolds, making high-dimensional dynamic optimization more tractable.

Why read it. If you work on expensive or large-scale dynamic optimization — supply chains, dynamic pricing, large engineering systems — this paper shows how to scale transfer-based methods to settings where they previously did not work.

Contribution. Transfers promising individuals instead of whole populations, enabling finer-grained adaptation.

Why read it. A clean conceptual move — from populations to individuals — that has been picked up by later work in evolutionary multi-task learning and surrogate-assisted optimization.

Contribution. Selects multilabel features by jointly optimizing relevance and redundancy, fast enough for practice.

Why read it. A practical, fast drop-in replacement for multi-label feature selection that improves results on standard benchmarks. Useful for anyone working on multi-label classification, tag recommendation, or hierarchical text categorization.

Contribution. Makes transfer decisions knowledge-guided: what to transfer, when, and how much.

Why read it. A principled way to make transfer decisions adaptive rather than fixed — a framework now widely followed in evolutionary multi-task and dynamic optimization research.

Contribution. Preserves label-group structure while selecting label-specific features.

Why read it. Targets the realistic case where labels come in groups (genres, disease categories, taxonomic levels) rather than as independent binary targets — directly useful for hierarchical and structured multi-label applications.

Contribution. Uses a mixture of predictors to match different change patterns in dynamic optimization.

Why read it. A modular and extensible framework for handling heterogeneous change dynamics — useful as a template for any predictive-transfer approach to non-stationary optimization.

Contribution. Adds scheduled synapses to spiking neural P systems, giving them explicit timing control.

Why read it. Useful as a clean introduction to spiking neural P systems for newcomers and as a standard reference when citing the scheduled-synapses extension in membrane-computing research.

Contribution. Scales feature selection with multitasking and filtering, making evolutionary search workable on high dimensions.

Why read it. A practical recipe for scaling evolutionary feature selection to problems where it previously could not run, with a clean multitasking formulation that generalizes to other large-scale sparse optimization tasks.

Contribution. Uses incremental SVM prediction to track changing Pareto fronts online.

Why read it. A useful reference for readers working on related problems.

Contribution. Uses lower-confidence bounds to pick transferable solutions in multitask optimization.

Why read it. A useful reference for readers working on related problems.

Contribution. Combines spatial structure and temporal change to improve constrained dynamic optimization.

Why read it. Extends transfer learning in dynamic optimization to the constrained setting, and introduces the novel idea of leveraging spatial structure in addition to temporal patterns.

Contribution. Turns fairness diagnostics into actionable explanations for graph neural networks.

Why read it. A useful reference for readers working on related problems.

Contribution. Stabilizes graph meta-learning by calibrating manifolds with proxy subgraphs.

Why read it. A useful reference for readers working on related problems.

Contribution. Finds transferable perturbations that break person re-ID across RGB and infrared.

Why read it. By combining gradients from RGB and infrared modalities with a grayscale bridge, the method learns a transferable perturbation that degrades re-ID performance across modalities while remaining visually subtle.

Contribution. Produces interpretable PDE solutions rather than opaque black-box approximations.

Why read it. A useful reference for readers working on related problems.

Contribution. Learns from multiple graph views to reduce label dependence in subgraph learning.

Why read it. A useful reference for readers working on related problems.

Contribution. Uses T-NNGP to produce interpretable multi-physics PDE solutions.

Why read it. A useful reference for readers working on related problems.

Contribution. Allocates computation dynamically to make evolutionary bilevel optimization practical.

Why read it. A useful reference for readers working on related problems.

Contribution. Turns image-to-text attacks into a decision-based black-box method with no gradients.

Why read it. A useful reference for readers working on related problems.

Contribution. Maps the AI methods, representations, and open problems in crystalline material discovery.

Why read it. The paper introduces common crystal representations, reviews deep learning models tailored to materials discovery tasks, and highlights remaining challenges and future directions.

Contribution. Aligns molecular predictions with chemical concepts for more faithful explanations.

Why read it. It gives a concrete route to explainable molecular property prediction without separating prediction quality from concept-level alignment, which is useful for trustworthy molecular AI.

Contribution. Uses alignment augmentation and knowledge transfer to bridge sketch/RGB re-ID with few labels.

Why read it. Alignment Augmentation and a Knowledge Transfer Catalyst are used to improve domain alignment and boost cross-modal generalization.

Contribution. Embeds physics in graph networks for stable long-horizon multiphysics simulation.

Why read it. A useful reference for readers working on related problems.

Contribution. Prunes symbolic regressors with physics residuals and sensitivity, yielding cleaner equations.

Why read it. A useful reference for readers working on related problems.

Contribution. Infers interpretable intrinsic dynamics from video with bilevel optimization.

Why read it. A useful reference for readers working on related problems.

Contribution. Makes neural operators respect interface physics in multiphase flow simulation.

Why read it. A useful reference for readers working on related problems.

Contribution. Exposes a universal black-box weakness in 3DGS watermarking systems.

Why read it. A useful reference for readers working on related problems.

Contribution. Generates 4D scenes that stay physically consistent across time and materials.

Why read it. A useful reference for readers working on related problems.