Arrow Research search

Author name cluster

Lining Xing

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.

2 papers
1 author row

Possible papers

2

EAAI Journal 2026 Journal Article

Formation efficacy assessment of high-speed air vehicle swarms via the continuous belief rule base with heterogeneous data augmentation

  • Haoran Zhang
  • Ruohan Yang
  • Wei He
  • Xiaobo Lv
  • Lining Xing

To date, high-speed air vehicle swarm (AVS) formations have been widely applied to military missions, while the attention paid to formation efficacy assessment of AVSs has been increasing due to its significant instruction. On the one hand, it is almost impractical to acquire complete formation efficacy data of high-speed AVSs through repetitive trial flights considering the excessive cost. On the other hand, the considerable importance military departments attach to explainability makes the application of numerous popular artificial intelligence (AI) models limited despite their advantage in terms of accuracy. Focused on the challenges of incomplete formation efficacy data and inexplicable AI models, in this paper, the continuous belief rule base with heterogeneous data augmentation is proposed as a framework. The heterogeneous data augmentation strategy is constructed as the auxiliary component to overcome the first challenge, while the continuous belief rule base (CBRB) model is established as the core component to conquer the second challenge. Besides, a module based on an improved version of the grey wolf optimizer is devised for tuning the hyperparameters of the CBRB model. Relevant computational experiments are carried out, demonstrating the validity and superiority of our proposal. It should be noted that this paper is the first piece that discusses the application of belief rule-based systems such a representative of symbolic AI in the engineering of high-speed AVS formation efficacy assessment. More in-depth work will be further undertaken.

Details DOI

NeurIPS Conference 2025 Conference Paper

A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows

  • Guansheng Peng
  • Lining Xing
  • Fuyan Ma
  • Aldy Gunawan
  • Guopeng Song
  • Pieter Vansteenwegen

Recent years have witnessed a surge of interest in solving combinatorial optimization problems (COPs) using machine learning techniques. Motivated by this trend, we propose a learning-augmented exact approach for tackling an NP-hard COP, the Orienteering Problem with Time Windows, which aims to maximize the total score collected by visiting a subset of vertices in a graph within their time windows. Traditional exact algorithms rely heavily on domain expertise and meticulous design, making it hard to achieve further improvements. By leveraging deep learning models to learn effective relaxations of problem restrictions from data, our approach enables significant performance gains in an exact dynamic programming algorithm. We propose a novel graph convolutional network that predicts the directed edges defining the relaxation. The network is trained in a supervised manner, using optimal solutions as high-quality labels. Experimental results demonstrate that the proposed learning-augmented algorithm outperforms the state-of-the-art exact algorithm, achieving a 38% speedup on Solomon’s benchmark and more than a sevenfold improvement on the more challenging Cordeau’s benchmark.

PDF Details
v2026.09.13