Author name cluster

Yaqing Hou

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.

12 papers

2 author rows

EAAI Journal 2025 Journal Article

An evolutionary multitasking algorithm for multi-objective feature selection using dual-perspective reduction

Mengyue Wang
Hongwei Ge
Xia Wang
Liang Sun
Yaqing Hou
Bin Li

Feature selection inherently involves two conflicting objectives: minimizing the number of selected features and maximizing the classification accuracy. The exponential growth of the search space and complex interactions between features make high-dimensional feature selection challenging. Existing multi-objective methods suffer from slow convergence and limited search capabilities. Moreover, there is a lack of efficient methods for identifying feature subsets with equivalent objective values, which could offer diverse options. To address these issues, this paper proposes an evolutionary multitasking algorithm for multi-objective feature selection using dual-perspective reduction, called DREA-FS. First, a dual-perspective dimensionality reduction strategy is designed to generate simplified and complementary tasks through improved filter-based and group-based methods, facilitating the rapid identification of promising regions. To enable effective information sharing, a dual-archive multitasking optimization mechanism is proposed, which incorporates a diversity archive to preserve feature subsets with equivalent performance and maintain diversity. Coupled with an elite archive that offers convergence guidance, this mechanism achieves a balance between convergence and diversity across tasks, thereby enhancing the ability to search for equivalent feature subsets. Experimental results on 21 datasets demonstrate that the proposed method outperforms state-of-the-art multi-objective algorithms in classification performance. Besides, DREA-FS can identify different feature subsets with equivalent objective values, supporting decision-makers with diverse options and better interpretability.

Details DOI

IJCAI Conference 2025 Conference Paper

EFormer: An Effective Edge-based Transformer for Vehicle Routing Problems

Dian Meng
Zhiguang Cao
Yaoxin Wu
Yaqing Hou
Hongwei Ge
Qiang Zhang

Recent neural heuristics for the Vehicle Routing Problem (VRP) primarily rely on node coordinates as input, which may be less effective in practical scenarios where real cost metrics—such as edge-based distances—are more relevant. To address this limitation, we introduce EFormer, an Edge-based Transformer model that uses edge as the sole input for VRPs. Our approach employs a precoder module with a mixed-score attention mechanism to convert edge information into temporary node embeddings. We also present a parallel encoding strategy characterized by a graph encoder and a node encoder, each responsible for processing graph and node embeddings in distinct feature spaces, respectively. This design yields a more comprehensive representation of the global relationships among edges. In the decoding phase, parallel context embedding and multi-query integration are used to compute separate attention mechanisms over the two encoded embeddings, facilitating efficient path construction. We train EFormer using reinforcement learning in an autoregressive manner. Extensive experiments on the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) reveal that EFormer outperforms established baselines on synthetic datasets, including large-scale and diverse distributions. Moreover, EFormer demonstrates strong generalization on real-world instances from TSPLib and CVRPLib. These findings confirm the effectiveness of EFormer’s core design in solving VRPs.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

MTRec: Learning to Align with User Preferences via Mental Reward Models

Mengchen Zhao
Yifan Gao
Yaqing Hou
Xiangyang Li
Pengjie Gu
Zhenhua Dong
Ruiming Tang
Yi Cai

Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a user might click on a news article because of its attractive headline, but end up feeling uncomfortable after reading the content. In the absence of explicit feedback, such erroneous implicit signals may severely mislead recommender systems. In this paper, we propose MTRec, a novel sequential recommendation framework designed to align with real user preferences by uncovering their internal satisfaction on recommended items. Specifically, we introduce a mental reward model to quantify user satisfaction and propose a distributional inverse reinforcement learning approach to learn it. The learned mental reward model is then used to guide recommendation models to better align with users’ real preferences. Our experiments show that MTRec brings significant improvements to a variety of recommendation models. We also deploy MTRec on an industrial short video platform and observe a 7\% increase in average user viewing time.

PDF Details

IJCAI Conference 2025 Conference Paper

Preference-based Deep Reinforcement Learning for Historical Route Estimation

Boshen Pan
Yaoxin Wu
Zhiguang Cao
Yaqing Hou
Guangyu Zou
Qiang Zhang

Recent Deep Reinforcement Learning (DRL) techniques have advanced solutions to Vehicle Routing Problems (VRPs). However, many of these methods focus exclusively on optimizing distance-oriented objectives (i. e. , minimizing route length), often overlooking the implicit drivers' preferences for routes. These preferences, which are crucial in practice, are challenging to model using traditional DRL approaches. To address this gap, we propose a preference-based DRL method characterized by its reward design and optimization objective, which is specialized to learn historical route preferences. Our experiments demonstrate that the method aligns generated solutions more closely with human preferences. Moreover, it exhibits strong generalization performance across a variety of instances, offering a robust solution for different VRP scenarios.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems

Dian Meng
Zhiguang Cao
Jie Gao
Yaoxin Wu
Yaqing Hou

Neural solvers for the Vehicle Routing Problem (VRP) have typically relied on either node or edge inputs, limiting their flexibility and generalization in real-world scenarios. We propose UniteFormer, a unified neural solver that supports node-only, edge-only, and hybrid input types through a single model trained via joint edge-node modalities. UniteFormer introduces: (1) a mixed encoder that integrates graph convolutional networks and attention mechanisms to collaboratively process node and edge features, capturing cross-modal interactions between them; and (2) a parallel decoder enhanced with query mapping and a feed-forward layer for improved representation. The model is trained with REINFORCE by randomly sampling input types across batches. Experiments on the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) demonstrate that UniteFormer achieves state-of-the-art performance and generalizes effectively to TSPLib and CVRPLib instances. These results underscore UniteFormer’s ability to handle diverse input modalities and its strong potential to improve performance across various VRP tasks.

PDF Details

AAMAS Conference 2024 Conference Paper

Collaborative Deep Reinforcement Learning for Solving Multi-Objective Vehicle Routing Problems

Yaoxin Wu
Mingfeng Fan
Zhiguang Cao
Ruobin Gao
Yaqing Hou
Guillaume Sartoretti

Existing deep reinforcement learning (DRL) methods for multiobjective vehicle routing problems (MOVRPs) typically decompose an MOVRP into subproblems with respective preferences and then train policies to solve corresponding subproblems. However, such a paradigm is still less effective in tackling the intricate interactions among subproblems, thus holding back the quality of the Pareto solutions. To counteract this limitation, we introduce a collaborative deep reinforcement learning method. We first propose a preferencebased attention network (PAN) that allows the DRL agents to reason out solutions to subproblems in parallel, where a shared encoder learns the instance embedding and a decoder is tailored for each agent by preference intervention to construct respective solutions. Then, we design a collaborative active search (CAS) to further improve the solution quality, which updates only a part of the decoder parameters per instance during inference. In the CAS process, we also explicitly foster the interactions of neighboring DRL agents by imitation learning, empowering them to exchange insights of elite solutions to similar subproblems. Extensive results on random and benchmark instances verified the efficacy of PAN and CAS, which is particularly pronounced on the configurations (i. e. , problem sizes or node distributions) beyond the training ones. Our code is available at https: //github. com/marmotlab/PAN-CAS.

PDF

IJCAI Conference 2024 Conference Paper

SAEIR: Sequentially Accumulated Entropy Intrinsic Reward for Cooperative Multi-Agent Reinforcement Learning with Sparse Reward

Xin He
Hongwei Ge
Yaqing Hou
Jincheng Yu

Multi-agent reinforcement learning (MARL) performs well for solving complex cooperative tasks when the scenarios have well-defined dense rewards. However, there are usually sparse reward settings in many real-world multi-agent systems, which makes it difficult for MARL algorithms to successfully learn an effective strategy. To tackle this problem, we propose a novel sequentially accumulated entropy intrinsic reward named SAEIR, which utilizes the entropy of multi-agent system as a bonus to accelerate learning. Specifically, the multi-scale hypergraph critic is proposed to obtain high-order system state representation, which also enhances the ability to effectively evaluate the action produced by the actor. Based on the comprehensive and compact system state representation, the orderliness of multi-agent systems can be measured to determine the highly valuable states for adding entropy-based intrinsic rewards which leads to a highly efficient learning process. Empirical results demonstrate that our proposed method achieves state-of-the-art performance in several complex cooperative multi-agent environments with sparse reward settings.

PDF Details DOI

AAMAS Conference 2023 Conference Paper

Improving Cooperative Multi-Agent Exploration via Surprise Minimization and Social Influence Maximization

Mingyang Sun
Yaqing Hou
Jie Kang
Haiyin Piao
Yifeng Zeng
Hongwei Ge
Qiang Zhang

In multi-agent reinforcement learning (MARL), the uncertainty of state change and the inconsistency between agents’ local observation and global information are always the main obstacles of cooperative multi-agent exploration. To address these challenges, we propose a novel MARL exploration method by combining surprise minimization and social influence maximization. Considering state entropy as a measure of surprise, surprise minimization is achieved by rewarding the individual’s intrinsic motivation (or rewards) for coping with more stable and familiar situations, hence promoting the policy learning. Furthermore, we introduce mutual information between agents’ actions as a regularizer to maximize the social influence via optimizing a tractable variational estimation. In this way, the agents are guided to interact positively with one another by navigating between states that favor cooperation.

PDF

IJCAI Conference 2022 Conference Paper

Budgeted Sequence Submodular Maximization

Xuefeng Chen
Liang Feng
Xin Cao
Yifeng Zeng
Yaqing Hou

The problem of selecting a sequence of items that maximizes a given submodular function appears in many real-world applications. Existing study on the problem only considers uniform costs over items, but non-uniform costs on items are more general. Taking this cue, we study the problem of budgeted sequence submodular maximization (BSSM), which introduces non-uniform costs of items into the sequence selection. This problem can be found in a number of applications such as movie recommendation, course sequence design and so on. Non-uniform costs on items significantly increase the solution complexity and we prove that BSSM is NP-hard. To solve the problem, we first propose a greedy algorithm GBM with an error bound. We also design an anytime algorithm POBM based on Pareto optimization to improve the quality of solutions. Moreover, we prove that POBM can obtain approximate solutions in expected polynomial running time, and converges faster than a state-of-the-art algorithm POSEQSEL for sequence submodular maximization with cardinality constraints. We further introduce optimizations to speed up POBM. Experimental results on both synthetic and real-world datasets demonstrate the performance of our new algorithms.

PDF Details DOI

ICAPS Conference 2022 Conference Paper

DOMA: Deep Smooth Trajectory Generation Learning for Real-Time UAV Motion Planning

Jin Yu
Haiyin Piao
Yaqing Hou
Li Mo 0001
Xin Yang 0011
Deyun Zhou

In this paper, we present a Deep Reinforcement Learning (DRL) based real-time smooth UAV motion planning method for solving catastrophic flight trajectory oscillation issues. By formalizing the original problem as a linear mixture of dual-objective optimization, a novel Deep smOoth Motion plAnning (DOMA) algorithm is proposed, which adopts an alternative layer-by-layer gradient descending optimization approach with the major gradient and the DOMA gradient applied separately. Afterward, the mix weight coefficient between the two objectives is also optimized adaptively. Experimental result reveals that the proposed DOMA algorithm outperforms baseline DRL-based UAV motion planning algorithms in terms of both learning efficiency and flight motion smoothness. Furthermore, the UAV safety issue induced by trajectory oscillation is also addressed.

Details

ICRA Conference 2022 Conference Paper

Towards Efficient 3D Human Motion Prediction using Deformable Transformer-based Adversarial Network

Hua Yu 0006
Xuanzhe Fan
Yaqing Hou
Yi Liu
Cai Kang
Dongsheng Zhou
Qiang Zhang 0008

Human motion prediction is a crucial step for achieving human-robot interactions. While recent transformer-based methods have shown great potentials in 3D human motion prediction, they still suffer from mode collapse to non-plausible poses and quadratically computational complexity with respect to the increasing length of input sequences. In this paper, we propose a novel spatio-temporal deformable transformer-based adversarial network (STDTA) for 3D human motion prediction. First, we design a spatio-temporal deformable transformer module to capture the correlations between human joints while reducing the computational costs. Second, we introduce the adversarial training mechanism and design fidelity and continuity discriminators to maintain smoothness and stability for the long-term prediction. Finally, extensive experiments on Human 3. 6M and AMASS benchmarks demonstrate that the proposed STDTA achieves state-of-the-art performance.

Details

AAMAS Conference 2016 Conference Paper

A Memetic Multi-Agent Demonstration Learning Approach with Behavior Prediction

Yaqing Hou
Yifeng Zeng
Yew-Soon Ong

Memetic Multi-Agent System (MeMAS) emerges as an enhanced version of multi-agent systems with the implementation of meme-inspired agents. Previous research of MeMAS has developed a computational framework in which a series of memetic operations have been designed for implementing multiple interacting agents. This paper further endeavors to address the speciﬁc challenges that arise in more complex multi-agent settings where agents share a common setting with other agents who have diﬀerent and even competitive objectives. Particularly, we propose a memetic multiagent demonstration learning approach (MeMAS-P) with improvement over existing work to allow agents to improve their performance by building candidate models and accordingly predicting behaviors of their opponents. Experiments based on an adapted mineﬁeld navigation task have shown that MeMAS-P could provide agents with ability to acquire increasing level of learning capability and reduce the candidate model space by sharing meme-inspired demonstrations with respect to their representative knowledge and unique candidate models.

PDF