Xu Yuan

EAAI Journal 2026 Journal Article

Adaptive multi-agent stock trading decision support system based on deep reinforcement learning

• Xu Yuan
• Jiaqiang Wang
• Shaokui Gu
• Yi Guo
• Ange Qi
• Shijin Li
• Liang Zhao

The stock market is a highly dynamic, complex, and uncertain environment, where traditional investment strategies and technical analysis tools often fail to provide reliable guidance, leading to increased investment risk and uncertainty. This study aims to develop an adaptive multi-agent stock trading decision support system that can effectively respond to volatile market conditions while balancing returns and risk management. We propose a deep reinforcement learning framework based on the Dueling Deep Q-Network (Dueling DQN) algorithm, in which multiple agents independently make optimal trading decisions based on the constructed environment state. The system incorporates a redesigned reward function, a dynamic exploration strategy, and a risk management mechanism to ensure real-time adaptation to market feedback. Extensive experiments on domestic and international market data demonstrate that the proposed system outperforms existing models, effectively responds to market shocks, and exhibits superior adaptability across different market conditions. The proposed multi-agent trading system achieves a robust balance between profitability and risk control, indicating its potential economic value and applicability in dynamic financial markets.

EAAI Journal 2026 Journal Article

Corrigendum to “Adaptive multi-agent stock trading decision support system based on deep reinforcement learning” [EAAI_114130]

• Xu Yuan
• Jiaqiang Wang
• Shaokui Gu
• Yi Guo
• Ange Qi
• Shijin Li
• Liang Zhao

AAAI Conference 2025 Conference Paper

Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model

• Xu Yuan
• Li Zhou
• Zenghui Sun
• Zikun Zhou
• Jinsong Lan

Large Multimodal Models (LMMs) have significantly progressed by extending large language models. Building on this progress, the latest developments in LMMs demonstrate the ability to generate dense pixel-wise segmentation by integrating segmentation models. Despite the innovations, existing works’ textual responses and segmentation masks remain at the instance level, showing limited ability to perform fine-grained understanding and segmentation even provided with detailed textual cues. To overcome this limitation, we introduce a Multi-Granularity Large Multimodal Model (MGLMM), which is capable of seamlessly adjusting the granularity of Segmentation and Captioning (SegCap) following user instructions, from panoptic SegCap to fine-grained SegCap. We name such a new task Multi-Granularity Segmentation and Captioning (MGSC). Observing the lack of a benchmark for model training and evaluation over the MGSC task, we establish a benchmark with aligned masks and captions in multi-granularity using our customized automated annotation pipeline. This benchmark comprises 10K images and more than 30K image-question pairs. We will release our dataset along with the implementation of our automated dataset annotation pipeline for further research. Besides, we propose a novel unified SegCap data format to unify heterogeneous segmentation datasets; it effectively facilitates learning to associate object concepts with visual features during multi-task training. Extensive experiments demonstrate that our MGLMM excels at tackling more than eight downstream tasks and achieves state-of-the-art performance in MGSC, GCG, image captioning, referring segmentation, multiple/empty segmentation, and reasoning segmentation. The great properties and versatility of MGLMM underscore its potential impact on advancing multimodal research.

NeurIPS Conference 2025 Conference Paper

Long-Tailed Recognition via Information-Preservable Two-Stage Learning

• Fudong Lin
• Xu Yuan

The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper, we propose a novel two-stage learning approach to mitigate such a majority-biased tendency while preserving valuable information within datasets. Specifically, the first stage proposes a new representation learning technique from the information theory perspective. This approach is theoretically equivalent to minimizing intra-class distance, yielding an effective and well-separated feature space. The second stage develops a novel sampling strategy that selects mathematically informative instances, able to rectify majority-biased decision boundaries without compromising a model’s overall performance. As a result, our approach achieves the state-of-the-art performance across various long-tailed benchmark datasets, validated via extensive experiments. Our code is available at https: //github. com/fudong03/BNS_IPDPP.

AAAI Conference 2024 Conference Paper

Cheaper and Faster: Distributed Deep Reinforcement Learning with Serverless Computing

• Hanfei Yu
• Jian Li
• Yang Hua
• Xu Yuan
• Hao Wang

Deep reinforcement learning (DRL) has gained immense success in many applications, including gaming AI, robotics, and system scheduling. Distributed algorithms and architectures have been vastly proposed (e.g., actor-learner architecture) to accelerate DRL training with large-scale server-based clusters. However, training on-policy algorithms with the actor-learner architecture unavoidably induces resource wasting due to synchronization between learners and actors, thus resulting in significantly extra billing. As a promising alternative, serverless computing naturally fits on-policy synchronization and alleviates resource wasting in distributed DRL training with pay-as-you-go pricing. Yet, none has leveraged serverless computing to facilitate DRL training. This paper proposes MinionsRL, the first serverless distributed DRL training framework that aims to accelerate DRL training- and cost-efficiency with dynamic actor scaling. We prototype MinionsRL on top of Microsoft Azure Container Instances and evaluate it with popular DRL tasks from OpenAI Gym. Extensive experiments show that MinionsRL reduces total training time by up to 52% and training cost by 86% compared to latest solutions.

AAAI Conference 2023 Conference Paper

DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness

• Gang Yan
• Hao Wang
• Xu Yuan
• Jian Li

Federated learning (FL) is known to be susceptible to model poisoning attacks in which malicious clients hamper the accuracy of the global model by sending manipulated model updates to the central server during the FL training process. Existing defenses mainly focus on Byzantine-robust FL aggregations, and largely ignore the impact of the underlying deep neural network (DNN) that is used to FL training. Inspired by recent findings on critical learning periods (CLP) in DNNs, where small gradient errors have irrecoverable impact on the final model accuracy, we propose a new defense, called a CLP-aware defense against poisoning of FL (DeFL). The key idea of DeFL is to measure fine-grained differences between DNN model updates via an easy-to-compute federated gradient norm vector (FGNV) metric. Using FGNV, DeFL simultaneously detects malicious clients and identifies CLP, which in turn is leveraged to guide the adaptive removal of detected malicious clients from aggregation. As a result, DeFL not only mitigates model poisoning attacks on the global model but also is robust to detection errors. Our extensive experiments on three benchmark datasets demonstrate that DeFL produces significant performance gain over conventional defenses against state-of-the-art model poisoning attacks.

IJCAI Conference 2021 Conference Paper

Improving Sequential Recommendation Consistency with Self-Supervised Imitation

• Xu Yuan
• Hongshen Chen
• Yonghao Song
• Xiaofang Zhao
• Zhuoye Ding

Most sequential recommendation models capture the features of consecutive items in a user-item interaction history. Though effective, their representation expressiveness is still hindered by the sparse learning signals. As a result, the sequential recommender is prone to make inconsistent predictions. In this paper, we propose a model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation. Precisely, we extract the consistency knowledge by utilizing three self-supervised pre-training tasks, where temporal consistency and persona consistency capture user-interaction dynamics in terms of the chronological order and persona sensitivities, respectively. Furthermore, to provide the model with a global perspective, global session consistency is introduced by maximizing the mutual information among global and local interaction sequences. Finally, to comprehensively take advantage of all three independent aspects of consistency-enhanced knowledge, we establish an integrated imitation learning framework. The consistency knowledge is effectively internalized and transferred to the student model by imitating the conventional prediction logit as well as the consistency-enhanced item representations. In addition, the flexible self-supervised imitation framework can also benefit other student recommenders. Experiments on four real-world datasets show that SSI effectively outperforms the state-of-the-art sequential recommendation methods.

IJCAI Conference 2021 Conference Paper

Interpretable Minority Synthesis for Imbalanced Classification

• Yi He
• Fudong Lin
• Xu Yuan
• Nian-Feng Tzeng

This paper proposes a novel oversampling approach that strives to balance the class priors with a considerably imbalanced data distribution of high dimensionality. The crux of our approach lies in learning interpretable latent representations that can model the synthetic mechanism of the minority samples by using a generative adversarial network(GAN). A Bayesian regularizer is imposed to guide the GAN to extract a set of salient features that are either disentangled or intensionally entangled, with their interplay controlled by a prescribed structure, defined with human-in-the-loop. As such, our GAN enjoys an improved sample complexity, being able to synthesize high-quality minority samples even if the sizes of minority classes are extremely small during training. Empirical studies substantiate that our approach can empower simple classifiers to achieve superior imbalanced classification performance over the state-of-the-art competitors and is robust across various imbalance settings. Code is released in github. com/fudonglin/IMSIC.

AAAI Conference 2021 Conference Paper

Online Learning in Variable Feature Spaces under Incomplete Supervision

• Yi He
• Xu Yuan
• Sheng Chen
• Xindong Wu

This paper explores a new online learning problem where the input sequence lives in an over-time varying feature space and the ground-truth label of any input point is given only occasionally, making online learners less restrictive and more applicable. The crux in this setting lies in how to exploit the very limited labels to efficiently update the online learners. Plausible ideas such as propagating labels from labeled points to their neighbors through uncovering the point-wise geometric relations face two challenges: (1) distance measurement fails to work as different points may be described by disparate sets of features and (2) storing the geometric shape, which is formed by all arrived points, is unrealistic in an online setting. To address these challenges, we first construct a universal feature space that accumulates all observed features, making distance measurement feasible. Then, we use manifolds to represent the geometric shapes and approximate them in a sparse means, making manifolds computational and memory tractable in online learning. We frame these two building blocks into a regularized risk minimization algorithm. Theoretical analysis and empirical evidence substantiate the viability and effectiveness of our proposal.

IJCAI Conference 2020 Conference Paper

Learning Interpretable Representations with Informative Entanglements

• Ege Beyazıt
• Doruk Tuncel
• Xu Yuan
• Nian-Feng Tzeng
• Xindong Wu

Learning interpretable representations in an unsupervised setting is an important yet a challenging task. Existing unsupervised interpretable methods focus on extracting independent salient features from data. However they miss out the fact that the entanglement of salient features may also be informative. Acknowledging these entanglements can improve the interpretability, resulting in extraction of higher quality and a wider variety of salient features. In this paper, we propose a new method to enable Generative Adversarial Networks (GANs) to discover salient features that may be entangled in an informative manner, instead of extracting only disentangled features. Specifically, we propose a regularizer to punish the disagreement between the extracted feature interactions and a given dependency structure while training. We model these interactions using a Bayesian network, estimate the maximum likelihood parameters and calculate a negative likelihood score to measure the disagreement. Upon qualitatively and quantitatively evaluating the proposed method using both synthetic and real-world datasets, we show that our proposed regularizer guides GANs to learn representations with disentanglement scores competing with the state-of-the-art, while extracting a wider variety of salient features.