Multitasking Evolutionary Algorithm Based on Adaptive Seed Transfer for Combinatorial Problem

• URL: http://arxiv.org/abs/2308.12647v1
• Date: Thu, 24 Aug 2023 08:43:32 GMT
• Title: Multitasking Evolutionary Algorithm Based on Adaptive Seed Transfer for Combinatorial Problem
• Authors: Haoyuan Lv, Ruochen Liu
• Abstract summary: evolutionary multitasking optimization (EMTO) has become an emerging topic in the EC community. M TEA-AST can adaptively transfer knowledge in both same-domain and cross-domain many-task environments. The proposed method shows competitive performance compared to other state-of-the-art EMTOs in experiments consisting of four COPs.
• Score: 2.869730777051168
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evolutionary computing (EC) is widely used in dealing with combinatorial optimization problems (COP). Traditional EC methods can only solve a single task in a single run, while real-life scenarios often need to solve multiple COPs simultaneously. In recent years, evolutionary multitasking optimization (EMTO) has become an emerging topic in the EC community. And many methods have been designed to deal with multiple COPs concurrently through exchanging knowledge. However, many-task optimization, cross-domain knowledge transfer, and negative transfer are still significant challenges in this field. A new evolutionary multitasking algorithm based on adaptive seed transfer (MTEA-AST) is developed for multitasking COPs in this work. First, a dimension unification strategy is proposed to unify the dimensions of different tasks. And then, an adaptive task selection strategy is designed to capture the similarity between the target task and other online optimization tasks. The calculated similarity is exploited to select suitable source tasks for the target one and determine the transfer strength. Next, a task transfer strategy is established to select seeds from source tasks and correct unsuitable knowledge in seeds to suppress negative transfer. Finally, the experimental results indicate that MTEA-AST can adaptively transfer knowledge in both same-domain and cross-domain many-task environments. And the proposed method shows competitive performance compared to other state-of-the-art EMTOs in experiments consisting of four COPs.

Related papers

• Towards Multi-Objective High-Dimensional Feature Selection via Evolutionary Multitasking [63.91518180604101]
  This paper develops a novel EMT framework for high-dimensional feature selection problems, namely MO-FSEMT. A task-specific knowledge transfer mechanism is designed to leverage the advantage information of each task, enabling the discovery and effective transmission of high-quality solutions.
  arXiv  Detail & Related papers  (2024-01-03T06:34:39Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• An Evolutionary Multitasking Algorithm with Multiple Filtering for High-Dimensional Feature Selection [17.63977212537738]
  evolutionary multitasking (EMT) has been successfully used in the field of high-dimensional classification. This paper devises a new EMT for FS in high-dimensional classification, which first adopts different filtering methods to produce multiple tasks. A competitive swarm is modified to simultaneously solve these relevant FS tasks by transferring useful knowledge among them.
  arXiv  Detail & Related papers  (2022-12-17T12:06:46Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)
• Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction [125.18248926508045]
  We propose Channel-Exchanging-Network (CEN) which is self-adaptive, parameter-free, and more importantly, applicable for both multimodal fusion and multitask learning. CEN dynamically exchanges channels betweenworks of different modalities. For the application of dense image prediction, the validity of CEN is tested by four different scenarios.
  arXiv  Detail & Related papers  (2021-12-04T05:47:54Z)
• AT-MFCGA: An Adaptive Transfer-guided Multifactorial Cellular Genetic Algorithm for Evolutionary Multitasking [17.120962133525225]
  We introduce a novel adaptive metaheuristic algorithm to deal with Evolutionary Multitasking environments. AT-MFCGA relies on cellular automata to implement mechanisms in order to exchange knowledge among the optimization problems under consideration.
  arXiv  Detail & Related papers  (2020-10-08T12:00:10Z)
• Weakly supervised cross-domain alignment with optimal transport [102.8572398001639]
  Cross-domain alignment between image objects and text sequences is key to many visual-language tasks. This paper investigates a novel approach for the identification and optimization of fine-grained semantic similarities between image and text entities.
  arXiv  Detail & Related papers  (2020-08-14T22:48:36Z)
• Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction [166.87111665908333]
  We propose a novel multi-task learning method called Task-Feature Collaborative Learning (TFCL) Specifically, we first propose a base model with a heterogeneous block-diagonal structure regularizer to leverage the collaborative grouping of features and tasks. As a practical extension, we extend the base model by allowing overlapping features and differentiating the hard tasks.
  arXiv  Detail & Related papers  (2020-04-29T02:32:04Z)
• Multifactorial Cellular Genetic Algorithm (MFCGA): Algorithmic Design, Performance Comparison and Genetic Transferability Analysis [17.120962133525225]
  Multiobjective optimization is an incipient research area which is lately gaining a notable research momentum. In this work we propose a novel algorithmic scheme for Multifactorial Optimization scenarios. The proposed MFCGA hinges on concepts from Cellular Automata to implement mechanisms for exchanging knowledge among problems.
  arXiv  Detail & Related papers  (2020-03-24T11:03:55Z)
• A Two stage Adaptive Knowledge Transfer Evolutionary Multi-tasking Based on Population Distribution for Multi/Many-Objective Optimization [12.53272339049236]
  This paper proposes a two-stage adaptive knowledge transfer evolutionary multi-tasking optimization algorithm based on population distribution. EMT-PD can accelerate and improve the convergence performance of tasks based on the knowledge extracted from the probability model. Experimental results on multi-tasking multi-objective optimization test suites show that EMT-PD is superior to other six state-of-the-art evolutionary multi/single-tasking algorithms.
  arXiv  Detail & Related papers  (2020-01-03T13:05:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.