Author name cluster

Hisao Ishibuchi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

EAAI Journal 2025 Journal Article

Critical nodes detection for complex networks via knowledge-guided evolutionary framework

Chanjuan Liu
Shike Ge
Zhihan Chen
Wenbin Pei
Enqiang Zhu
Hisao Ishibuchi

The Critical Node Problem (CNP) focuses on identifying critical nodes within complex networks. These nodes play a crucial role in maintaining connectivity, and their removal impacts network performance. Among CNP variants, CNP-1a — which minimizes pairwise connectivity after removing a limited number of nodes — has attracted significant research attention due to its NP-hard nature and applications in diverse fields like epidemic control and infrastructure resilience. While state-of-the-art methods leverage memetic algorithms and variable populations, they fundamentally rely on random initialization that often converges to local optima. This limitation arises because traditional methods fail to capture higher-order topological dependencies. To address this gap, we propose K2GA, a knowledge-guided genetic algorithm initialized by a graph attention network (GAT). The GAT embeds networks into low-dimensional spaces, assigning topology-aware attention weights to nodes that guide population initialization. K2GA then employs a hybrid genetic algorithm with a local search process to identify an optimal set of critical nodes. The local search process utilizes a cut node-based greedy strategy. Experiments on 26 real-world networks demonstrate that K2GA outperforms state-of-the-art methods in terms of the best, median, and average objective values, establishing new upper bounds for minimization in eight cases. This work pioneers a GAT-guided evolutionary search framework, offering a novel paradigm for solving CNP.

Details DOI

AAAI Conference 2025 Conference Paper

Multi-Objective Molecular Design Through Learning Latent Pareto Set

Yiping Liu
Jiahao Yang
Xuanbai Ren
Zhang Xinyi
Yuansheng Liu
Bosheng Song
Xiangxiang Zeng
Hisao Ishibuchi

Molecular design inherently involves the optimization of multiple conflicting objectives, such as enhancing bio-activity and ensuring synthesizability. Evaluating these objectives often requires resource-intensive computations or physical experiments. Current molecular design methodologies typically approximate the Pareto set using a limited number of molecules. In this paper, we present an innovative approach, called Multi-Objective Molecular Design through Learning Latent Pareto Set (MLPS). MLPS initially utilizes an encoder-decoder model to seamlessly transform the discrete chemical space into a continuous latent space. We then employ local Bayesian optimization models to efficiently search for local optimal solutions (i.e., molecules) within predefined trust regions. Using surrogate objective values derived from these local models, we train a global Pareto set learning model to understand the mapping between direction vectors (called “preferences”) in the objective space and the entire Pareto set in the continuous latent space. Both the global Pareto set learning model and local Bayesian optimization models collaborate to discover high-quality solutions and adapt the trust regions dynamically. Our work is an effective endeavor towards learning the Pareto set for multi-objective molecular design, providing decision-makers with the capability to fine-tune their preferences and thoroughly explore the Pareto set. Experimental results demonstrate that MLPS achieves state-of-the-art performance across various multi-objective scenarios, encompassing diverse objective types and varying numbers of objectives. The effectiveness of MLPS was further validated through real-world challenges in discovering antifungal peptides with low toxicity and high activity.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning

Hiroki Shiraishi
Hisao Ishibuchi
Masaya Nakata

Function approximation is a critical task in various fields. However, existing neural network approaches struggle with locally complex or discontinuous functions due to their reliance on a single global model covering the entire problem space. We propose X-KAN, a novel method that optimizes multiple local Kolmogorov-Arnold Networks (KANs) through an evolutionary rule-based machine learning framework called XCSF. X-KAN combines KAN's high expressiveness with XCSF's adaptive partitioning capability by implementing local KAN models as rule consequents and defining local regions via rule antecedents. Our experimental results on artificial test functions and real-world datasets demonstrate that X-KAN significantly outperforms conventional methods, including XCSF, Multi-Layer Perceptron, and KAN, in terms of approximation accuracy. Notably, X-KAN effectively handles functions with locally complex or discontinuous structures that are challenging for conventional KAN, using a compact set of rules (average 7. 2 rules). These results validate the effectiveness of using KAN as a local model in XCSF, which evaluates the rule fitness based on both accuracy and generality. Our X-KAN implementation and an extended version of this paper, including appendices, are available at https: //doi. org/10. 48550/arXiv. 2505. 14273.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Learning Pareto Set for Multi-Objective Continuous Robot Control

Tianye Shu
Ke Shang
Cheng Gong
Yang Nan
Hisao Ishibuchi

For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multi-objective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single hypernet. The learned hypernet can directly generate various well-trained policy networks for different user preferences. We compare our method with two state-of-the-art MORL algorithms on seven multi-objective continuous robot control problems. Experimental results show that our method achieves the best overall performance with the least training parameters. An interesting observation is that the Pareto set is well approximated by a curved line or surface in a high-dimensional parameter space. This observation will provide insight for researchers to design new MORL algorithms.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework

Weiduo Liao
Ying Wei
Mingchen Jiang
Qingfu Zhang
Hisao Ishibuchi

Compositionality facilitates the comprehension of novel objects using acquired concepts and the maintenance of a knowledge pool. This is particularly crucial for continual learners to prevent catastrophic forgetting and enable compositionally forward transfer of knowledge. However, the existing state-of-the-art benchmarks inadequately evaluate the capability of compositional generalization, leaving an intriguing question unanswered. To comprehensively assess this capability, we introduce two vision benchmarks, namely Compositional GQA (CGQA) and Compositional OBJects365 (COBJ), along with a novel evaluation framework called Compositional Few-Shot Testing (CFST). These benchmarks evaluate the systematicity, productivity, and substitutivity aspects of compositional generalization. Experimental results on five baselines and two modularity-based methods demonstrate that current continual learning techniques do exhibit somewhat favorable compositionality in their learned feature extractors. Nonetheless, further efforts are required in developing modularity-based approaches to enhance compositional generalization. We anticipate that our proposed benchmarks and evaluation protocol will foster research on continual learning and compositionality.

PDF Details

ECAI Conference 2020 Conference Paper

A New Framework of Evolutionary Multi-Objective Algorithms with an Unbounded External Archive

Hisao Ishibuchi
Lie Meng Pang
Ke Shang 0004

This paper proposes a new framework for the design of evolutionary multi-objective optimization (EMO) algorithms. The main characteristic feature of the proposed framework is that the optimization result of an EMO algorithm is not the final population but a subset of the examined solutions during its execution. As a post-processing procedure, a pre-specified number of solutions are selected from an unbounded external archive where all the examined solutions are stored. In the proposed framework, the final population does not have to be a good solution set. The point of the algorithm design is to examine a wide variety of solutions over the entire Pareto front and to select well-distributed solutions from the archive. In this paper, first we explain difficulties in the design of EMO algorithms in the existing two frameworks: non-elitist and elitist. Next we propose the new framework of EMO algorithms. Then we demonstrate advantages of the proposed framework over the existing ones through computational experiments. Finally we suggest some interesting and promising future research topics.

Details

ECAI Conference 2020 Conference Paper

Many-Objective Problems Are Not Always Difficult for Pareto Dominance-Based Evolutionary Algorithms

Hisao Ishibuchi
Takashi Matsumoto
Naoki Masuyama
Yusuke Nojima

Recently, it has repeatedly been reported that the search ability of Pareto dominance-based multi-objective evolutionary algorithms severely deteriorates with the increase in the number of objectives. In this paper, we examine the generality of the reported observations through computational experiments on a wide variety of test problems. First, we generate 18 types of test problems by combining various properties of Pareto fronts and feasible regions. Next, we examine the performance of a frequently-used Pareto dominance-based evolutionary algorithm called NSGA-II on the generated test problems in comparison with four decomposition-based algorithms. We observe that the performance of NSGA-II severely degrades for three types of many-objective test problems which are similar to frequently-used DTLZ1-4 test problems with triangular Pareto fronts. However, better results are obtained by NSGA-II than all the examined decomposition-based algorithms for nine types of test problems even when they have ten objectives. Then, we discuss why NSGA-II does not work well on DTLZ type test problems whereas it works well on other test problems.

Details

TIST Journal 2016 Journal Article

Enhanced Knowledge-Leverage-Based TSK Fuzzy System Modeling for Inductive Transfer Learning

Zhaohong Deng
Yizhang Jiang
Hisao Ishibuchi
Kup-Sze Choi
Shitong Wang

The knowledge-leverage-based Takagi--Sugeno--Kang fuzzy system (KL-TSK-FS) modeling method has shown promising performance for fuzzy modeling tasks where transfer learning is required. However, the knowledge-leverage mechanism of the KL-TSK-FS can be further improved. This is because available training data in the target domain are not utilized for the learning of antecedents and the knowledge transfer mechanism from a source domain to the target domain is still too simple for the learning of consequents when a Takagi--Sugeno--Kang fuzzy system (TSK-FS) model is trained in the target domain. The proposed method, that is, the enhanced KL-TSK-FS (EKL-TSK-FS), has two knowledge-leverage strategies for enhancing the parameter learning of the TSK-FS model for the target domain using available information from the source domain. One strategy is used for the learning of antecedent parameters, while the other is for consequent parameters. It is demonstrated that the proposed EKL-TSK-FS has higher transfer learning abilities than the KL-TSK-FS. In addition, the EKL-TSK-FS has been further extended for the scene of the multisource domain.

Details DOI