Generalized Category Discovery (GCD) aims to classify unlabeled data by leveraging knowledge from labeled categories. While existing methods have achieved remarkable progress, they often treat images as flat feature sets, neglecting the intrinsic hierarchy: where key objects dominate meaning and backgrounds serve as context. For instance, in images of a dog either standing on grass or lying on a bed, the dog remains the central semantic element, whereas the background varies. Motivated by this, we propose LEArning Intrinsic Hierarchy (LEAH), a lightweight plug-and-play module designed to model hierarchical structure within images. LEAH consists of two components: a pruner that filters task-irrelevant tokens to extract key objects, and a constructor that embeds key objects and full images into hyperbolic space using adaptive entailment cones to capture compositional semantics. LEAH can be easily integrated into existing GCD frameworks with minimal modification. When applied to SimGCD, it achieves up to 13.2% accuracy improvement on fine-grained benchmarks, demonstrating its effectiveness in discovering subtle inter-class differences through hierarchical modeling.

Task allocation in multiagent systems is a critical challenge due to the heterogeneity of tasks and agents, where tasks have varying resource requirements and agents possess differing resource supplies. During execution, agents' resources deplete while tasks' requirements dynamically decrease. This problem has broad applications, such as optimally deploying UAVs equipped with diverse medical supplies in disaster rescue scenarios to minimize casualties. To address this, this article proposes a coalition formation game model, formulated as a potential game. We theoretically prove the submodularity of both the coalition utility function and the global utility function. Based on this submodularity, we establish that the efficiency lower bound of any Nash equilibrium in the proposed game model is given by $e / (2e-1)$ , significantly outperforming the 50% bound reported in prior studies. Furthermore, we introduce an inertia-based log-linear learning algorithm enhanced with a multiagent cooperative exchange mechanism, which enables the system to escape from suboptimal equilibria and improve global utility. In addition, we extend the algorithm to accommodate local communication constraints and dynamic allocation scenarios. Extensive experimental evaluations demonstrate that our proposed method achieves superior performance across diverse scenarios compared to existing algorithms.

Federated learning is a distributed machine learning system that uses participants’ data to train an improved global model. In federated learning, participants collaboratively train a global model, and after the training is completed, each participant receives that global model along with an incentive. Rational participants try to maximize their individual utility, and they will not input their high-quality data truthfully unless they are provided with satisfactory payments based on their contributions. Furthermore, federated learning benefits from the cooperation of participants. Accordingly, how to establish an incentive mechanism that both incentivizes inputting data truthfully and promotes cooperative contributions has become an important issue to consider. In this article, we introduce a data sharing game model for federated learning and employ game-theoretic approaches to design a core-selecting incentive mechanism by utilizing a popular concept in cooperative games, the core. In federated learning, the core can be empty, resulting in the core-selecting mechanism becoming infeasible. To address this issue, our core-selecting mechanism employs a relaxation method and simultaneously minimizes the benefits of inputting false data for all participants. Meanwhile, to reduce the computational complexity of the core-selecting mechanism, we propose an efficient core-selecting mechanism based on sampling approximation that only aggregates models on sampled coalitions to approximate the exact result. Extensive experiments demonstrate that the efficient core-selecting mechanism can incentivize truthful input of high-quality data and promote cooperation effectively, while it reduces computational overhead compared to the core-selecting mechanism.