Author name cluster

Yao Wang

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.

14 papers

2 author rows

JBHI Journal 2026 Journal Article

MVTT-GMamba: A Multimodal Graph Reasoning Framework for Anti-VEGF Efficacy Prediction in Diabetic Macular Edema

Shijing Wu
Yifan Zheng
Tianyu Chen
Gang Wu
Qinkun Zhi
Ailing Sui
Haixia Bai
Junhui Shen

Accurately predicting individual responses to Anti-Vascular Endothelial Growth Factor (Anti-VEGF) efficacy in diabetic macular edema (DME) remains a critical challenge in personalized ophthalmic care. Existing methods often rely on unimodal data or suffer from ineffective multimodal feature extraction and fusion, leading to modality redundancy and performance degradation. To address these limitations, we propose MVTT-GMamba, a novel multimodal learning framework that integrates optical coherence tomography (OCT) images and structured clinical indicators for early and accurate Anti-VEGF efficacy prediction. At the core of MVTT-GMamba is a feature-wise heterogeneous graph reasoning paradigm that explicitly models inter-patient and inter-feature relations, together with an adaptive, graph-guided prediction head that progressively anneals structural priors into the classifier. Building on this core, we adopt domain-tailored MambaVision and TabTransformer encoders and an early cross-attention fusion module to realize fine-grained multimodal representation learning. Extensive experiments on both a private clinical dataset (DMETHERA-ECSAHZU) and the public APTOS2021 benchmark demonstrate that MVTT-GMamba consistently outperforms state-of-the-art methods across all evaluation metrics. In addition, Grad-CAM visualizations reveal that the model attends to clinically relevant retinal regions, providing enhanced interpretability. Code is available at: https://github.com/DME666/DME.

Details DOI

JMLR Journal 2025 Journal Article

Kernel-based L_2-Boosting with Structure Constraints

Yao Wang
Xin Guo
Shao-Bo Lin

Developing efficient kernel methods for regression is popular in the past two decades. In this paper, utilizing boosting on kernel-based weak learners, we propose a novel kernel-based learning algorithm called kernel-based re-scaled boosting with truncation, dubbed as KReBooT. The proposed KReBooT benefits in controlling the structure and producing sparse estimators, and is near overfitting resistant. We conduct both theoretical analysis and numerical simulations to illustrate the excellent performance of KReBooT. Theoretically, we prove that KReBooT can achieve the optimal numerical convergence rate for nonlinear approximation. Furthermore, using a variant of Talagrand's concentration inequality, we provide fast learning rates for KReBooT, which is a new record of boosting-type algorithms. Numerically, we carry out several simulations to show the promising performance of KReBooT in terms of its good generalization, near over-fitting resistance and structure constraints. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

ICLR Conference 2025 Conference Paper

Offline Model-Based Optimization by Learning to Rank

Rong-Xi Tan
Ke Xue 0001
Shen-Huan Lyu
Haopu Shang
Yao Wang
Yaoyuan Wang
Sheng Fu
Chao Qian 0001

Offline model-based optimization (MBO) aims to identify a design that maximizes a black-box function using only a fixed, pre-collected dataset of designs and their corresponding scores. This problem has garnered significant attention from both scientific and industrial domains. A common approach in offline MBO is to train a regression-based surrogate model by minimizing mean squared error (MSE) and then find the best design within this surrogate model by different optimizers (e.g., gradient ascent). However, a critical challenge is the risk of out-of-distribution errors, i.e., the surrogate model may typically overestimate the scores and mislead the optimizers into suboptimal regions. Prior works have attempted to address this issue in various ways, such as using regularization techniques and ensemble learning to enhance the robustness of the model, but it still remains. In this paper, we argue that regression models trained with MSE are not well-aligned with the primary goal of offline MBO, which is to \textit{select} promising designs rather than to predict their scores precisely. Notably, if a surrogate model can maintain the order of candidate designs based on their relative score relationships, it can produce the best designs even without precise predictions. To validate it, we conduct experiments to compare the relationship between the quality of the final designs and MSE, finding that the correlation is really very weak. In contrast, a metric that measures order-maintaining quality shows a significantly stronger correlation. Based on this observation, we propose learning a ranking-based model that leverages learning to rank techniques to prioritize promising designs based on their relative scores. We show that the generalization error on ranking loss can be well bounded. Empirical results across diverse tasks demonstrate the superior performance of our proposed ranking-based method than twenty existing methods. Our implementation is available at \url{https://github.com/lamda-bbo/Offline-RaM}.

Details

NeurIPS Conference 2025 Conference Paper

Sequential Multi-Agent Dynamic Algorithm Configuration

Chen Lu
Ke Xue
Lei Yuan
Yao Wang
Yaoyuan Wang
Sheng Fu
Chao Qian

The performance of an algorithm often critically depends on its hyperparameter configuration. Dynamic algorithm configuration (DAC) is a recent trend in automated machine learning, which can dynamically adjust the algorithm’s configuration during the execution process and relieve users from tedious trial-and-error tuning tasks. Recently, multi-agent reinforcement learning (MARL) approaches have improved the configuration of multiple heterogeneous hyperparameters, making various parameter configurations for complex algorithms possible. However, many complex algorithms have inherent inter-dependencies among multiple parameters (e. g. , determining the operator type first and then the operator's parameter), which are, however, not considered in previous approaches, thus leading to sub-optimal results. In this paper, we propose the sequential multi-agent DAC (Seq-MADAC) framework to address this issue by considering the inherent inter-dependencies of multiple parameters. Specifically, we propose a sequential advantage decomposition network, which can leverage action-order information through sequential advantage decomposition. Experiments from synthetic functions to the configuration of multi-objective optimization algorithms demonstrate Seq-MADAC's superior performance over state-of-the-art MARL methods and show strong generalization across problem classes. Seq-MADAC establishes a new paradigm for the widespread dependency-aware automated algorithm configuration. Our code is available at https: //github. com/lamda-bbo/seq-madac.

PDF Details

ICML Conference 2025 Conference Paper

Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings

Rong-Xi Tan
Ming Chen
Ke Xue 0001
Yao Wang
Yaoyuan Wang
Sheng Fu
Chao Qian 0001

The pursuit of universal black-box optimization (BBO) algorithms is a longstanding goal. However, unlike domains such as language or vision, where scaling structured data has driven generalization, progress in offline BBO remains hindered by the lack of unified representations for heterogeneous numerical spaces. Thus, existing offline BBO approaches are constrained to single-task and fixed-dimensional settings, failing to achieve cross-domain universal optimization. Recent advances in language models (LMs) offer a promising path forward: their embeddings capture latent relationships in a unifying way, enabling universal optimization across different data types possible. In this paper, we discuss multiple potential approaches, including an end-to-end learning framework in the form of next-token prediction, as well as prioritizing the learning of latent spaces with strong representational capabilities. To validate the effectiveness of these methods, we collect offline BBO tasks and data from open-source academic works for training. Experiments demonstrate the universality and effectiveness of our proposed methods. Our findings suggest that unifying language model priors and learning string embedding space can overcome traditional barriers in universal BBO, paving the way for general-purpose BBO algorithms. The code is provided at https: //github. com/lamda-bbo/universal-offline-bbo.

Details

AAAI Conference 2024 Conference Paper

UNEX-RL: Reinforcing Long-Term Rewards in Multi-Stage Recommender Systems with UNidirectional EXecution

Gengrui Zhang
Yao Wang
Xiaoshuang Chen
Hongyi Qian
Kaiqiao Zhan
Ben Wang

In recent years, there has been a growing interest in utilizing reinforcement learning (RL) to optimize long-term rewards in recommender systems. Since industrial recommender systems are typically designed as multi-stage systems, RL methods with a single agent face challenges when optimizing multiple stages simultaneously. The reason is that different stages have different observation spaces, and thus cannot be modeled by a single agent. To address this issue, we propose a novel UNidirectional-EXecution-based multi-agent Reinforcement Learning (UNEX-RL) framework to reinforce the long-term rewards in multi-stage recommender systems. We show that the unidirectional execution is a key feature of multi-stage recommender systems, bringing new challenges to the applications of multi-agent reinforcement learning (MARL), namely the observation dependency and the cascading effect. To tackle these challenges, we provide a cascading information chain (CIC) method to separate the independent observations from action-dependent observations and use CIC to train UNEX-RL effectively. We also discuss practical variance reduction techniques for UNEX-RL. Finally, we show the effectiveness of UNEX-RL on both public datasets and an online recommender system with over 100 million users. Specifically, UNEX-RL reveals a 0.558% increase in users' usage time compared with single-agent RL algorithms in online A/B experiments, highlighting the effectiveness of UNEX-RL in industrial recommender systems.

PDF Details DOI

JBHI Journal 2023 Journal Article

A Spatiotemporal Graph Attention Network Based on Synchronization for Epileptic Seizure Prediction

Yao Wang
Yufei Shi
Yinlin Cheng
Zhipeng He
Xiaoyan Wei
Ziyi Chen
Yi Zhou

Accurate early prediction of epileptic seizures can provide timely treatment for patients. Previous studies have mainly focused on a single temporal or spatial dimension, making it difficult to take both relationships into account. Therefore, the effective properties of electroencephalograms (EEGs) may not be fully evaluated. To solve this problem, we propose a spatiotemporal graph attention network (STGAT) based on synchronization. The spatial and functional connectivity information between EEG channels was extracted by using the phase locking values (PLVs) first, which allowed multichannel EEG signals to be modeled as graph signals. Afterward, the STGAT model was used to dynamically learn the temporal correlation properties of EEG sequences and explore the spatial topological structure information of multiple channels. Experimental results demonstrated that the STGAT model was able to obtain spatiotemporal correlations and achieve good results on two benchmark datasets. The accuracy, specificity and sensitivity were 98. 74%, 99. 21% and 98. 87%, respectively, on the CHB-MIT dataset. Moreover, all evaluation indices of the private dataset had reached more than 98. 8%, with the area under the curve (AUC) reaching 99. 96%. The proposed method is superior or comparable to the state-of-the-art models. Extensive experiments demonstrate that our end-to-end automatic seizure prediction model can be extended to design clinical assistant decision systems.

Details DOI

JMLR Journal 2022 Journal Article

Nystrom Regularization for Time Series Forecasting

Zirui Sun
Mingwei Dai
Yao Wang
Shao-Bo Lin

This paper focuses on learning rate analysis of Nystrom regularization with sequential sub-sampling for $\tau$-mixing time series. Using a recently developed Banach-valued Bernstein inequality for $\tau$-mixing sequences and an integral operator approach based on second-order decomposition, we succeed in deriving almost optimal learning rates of Nystrom regularization with sequential sub-sampling for $\tau$-mixing time series. A series of numerical experiments are carried out to verify our theoretical results, showing the excellent learning performance of Nystrom regularization with sequential sub-sampling in learning massive time series data. All these results extend the applicable range of Nystr\"{o}m regularization from i.i.d. samples to non-i.i.d. sequences. [abs] [ pdf ][ bib ] &copy JMLR 2022. ( edit, beta )

PDF Details

IROS Conference 2021 Conference Paper

Double-Dot Network for Antipodal Grasp Detection

Yao Wang
Yangtao Zheng
Boyang Gao
Di Huang 0001

This paper proposes a new deep learning approach to antipodal grasp detection, named Double-Dot Network (DD-Net). It follows the recent anchor-free object detection framework, which does not depend on empirically pre-set anchors and thus allows more generalized and flexible prediction on unseen objects. Specifically, unlike the widely used 5-dimensional rectangle, the gripper configuration is defined as a pair of fingertips. An effective CNN architecture is introduced to localize such fingertips, and with the help of auxiliary centers for refinement, it accurately and robustly infers grasp candidates. Additionally, we design a specialized loss function to measure the quality of grasps, and in contrast to the IoU scores of bounding boxes adopted in object detection, it is more consistent to the grasp detection task. Both the simulation and robotic experiments are executed and state of the art accuracies are achieved, showing that DD-Net is superior to the counterparts in handling unseen objects.

Details

EAAI Journal 2021 Journal Article

Learning scalable multi-agent coordination by spatial differentiation for traffic signal control

Junjia Liu
Huimin Zhang
Zhuang Fu
Yao Wang

The intelligent control of the traffic signal is critical to the optimization of transportation systems. To achieve global optimal traffic efficiency in large-scale road networks, recent works have focused on coordination among intersections, which have shown promising results. However, existing studies paid more attention to observations sharing among intersections (both explicit and implicit) and did not care about the consequences after decisions. In this paper, we design a multi-agent coordination framework based on Deep Reinforcement Learning method for traffic signal control, defined as γ -Reward that includes both original γ -Reward and γ -Attention-Reward. Specifically, we propose the Spatial Differentiation method for coordination which uses the temporal–spatial information in the replay buffer to amend the reward of each action. A concise theoretical analysis that proves the proposed model can converge to Nash equilibrium is given. By extending the idea of Markov Chain to the dimension of space–time, this truly decentralized coordination mechanism replaces the graph attention method and realizes the decoupling of the road network, which is more scalable and more in line with practice. The simulation results show that the proposed model remains a state-of-the-art performance even not use a centralized setting. Code is available in https: //github. com/Skylark0924/Gamma_Reward.

Details DOI

AIIM Journal 2020 Journal Article

Real-world data medical knowledge graph: construction and applications

Linfeng Li
Peng Wang
Jun Yan
Yao Wang
Simin Li
Jinpeng Jiang
Zhe Sun
Buzhou Tang

Objective Medical knowledge graph (KG) is attracting attention from both academic and healthcare industry due to its power in intelligent healthcare applications. In this paper, we introduce a systematic approach to build medical KG from electronic medical records (EMRs) with evaluation by both technical experiments and end to end application examples. Materials and Methods The original data set contains 16, 217, 270 de-identified clinical visit data of 3, 767, 198 patients. The KG construction procedure includes 8 steps, which are data preparation, entity recognition, entity normalization, relation extraction, property calculation, graph cleaning, related-entity ranking, and graph embedding respectively. We propose a novel quadruplet structure to represent medical knowledge instead of the classical triplet in KG. A novel related-entity ranking function considering probability, specificity and reliability (PSR) is proposed. Besides, probabilistic translation on hyperplanes (PrTransH) algorithm is used to learn graph embedding for the generated KG. Results A medical KG with 9 entity types including disease, symptom, etc. was established, which contains 22, 508 entities and 579, 094 quadruplets. Compared with term frequency - inverse document frequency (TF/IDF) method, the normalized discounted cumulative gain (NDCG@10) increased from 0. 799 to 0. 906 with the proposed ranking function. The embedding representation for all entities and relations were learned, which are proven to be effective using disease clustering. Conclusion The established systematic procedure can efficiently construct a high-quality medical KG from large-scale EMRs. The proposed ranking function PSR achieves the best performance under all relations, and the disease clustering result validates the efficacy of the learned embedding vector as entity’s semantic representation. Moreover, the obtained KG finds many successful applications due to its statistics-based quadruplet. where N c o m i n is a minimum co-occurrence number and R is the basic reliability value. The reliability value can measure how reliable is the relationship between Si and Oij. The reason for the definition is the higher value of N co(Si, Oij ), the relationship is more reliable. However, the reliability values of the two relationships should not have a big difference if both of their co-occurrence numbers are very big. In our study, we finally set N c o m i n = 10 and R = 1 after some experiments. For instance, if co-occurrence numbers of three relationships are 1, 100 and 10000, their reliability values are 1, 2. 96 and 5 respectively.

Details DOI

YNICL Journal 2019 Journal Article

Asymmetry in cortical thickness and subcortical volume in treatment-naïve major depressive disorder

Zhiwei Zuo
Shuhua Ran
Yao Wang
Chang Li
Qi Han
Qianying Tang
Wei Qu
Haitao Li

BACKGROUND: Numerous cognitive and emotional functions are executed asymmetrically between the left and right hemispheres. Right hemisphere hyperactivity/left hemisphere hypoactivity often appears to be a feature in neuroimaging studies of depression. However, few studies have evaluated abnormalities in structural asymmetry in untreated patients with major depressive disorder (MDD). METHODS: In this study, 3-dimensional high-resolution structural magnetic resonance images were acquired from 35 treatment-naïve patients with MDD (mean age = 28.9 years, 22 females) and 35 normal controls. The asymmetry index in cortical thickness and subcortical volume were calculated based on an automated surface-based technique. RESULTS: Abnormalities in structural asymmetry in patients with MDD were mainly located in the cortical-striatal-pallidal-thalamic circuit, including the superior frontal cortex, rostral middle frontal cortex, caudal middle frontal cortex, nucleus accumbens, pallidum and thalamus. No significant correlation was observed between symptom severity and asymmetric measurements. CONCLUSION: These findings provide further evidence for the altered morphological interhemispheric imbalances in depression and these alterations were independent of depressive symptom severity, suggesting that cerebral asymmetry could be an appropriate indicator of morphological variations in mental disease.

Details DOI

YNICL Journal 2019 Journal Article

Structural brain network measures are superior to vascular burden scores in predicting early cognitive impairment in post stroke patients with small vessel disease

Jing Du
Yao Wang
Nan Zhi
Jieli Geng
Wenwei Cao
Ling Yu
Jianhua Mi
Yan Zhou

OBJECTIVES: In this cross-sectional study, we aimed to explore the mechanisms of early cognitive impairment in a post stroke non-dementia cerebral small vessel disease (SVD) cohort by comparing the SVD score with the structural brain network measures. METHOD: 127 SVD patients were recruited consecutively from a stroke clinic, comprising 76 individuals with mild cognitive impairment (MCI) and 51 with no cognitive impairment (NCI). Detailed neuropsychological assessments and multimodal MRI were performed. SVD scores were calculated on a standard scale, and structural brain network measures were analyzed by diffusion tensor imaging (DTI). Between-group differences were analyzed, and logistic regression was applied to determine the predictive value of SVD and network measures for cognitive status. Mediation analysis with structural equation modeling (SEM) was used to better understand the interactions of SVD burden, brain networks and cognitive deficits. RESULTS: ) was significantly related to cognitive state (p < .01) but not the SVD score. Mediation analysis showed that the standardized total effect (p = .013) and the standardized indirect effect (p = .016) of SVD score on cognition was significant, but the direct effect was not. CONCLUSIONS: Brain network measures, but not the SVD score, are significantly correlated with cognition in post-stroke SVD patients. Mediation analysis showed that the cerebral vascular lesions produce cognitive dysfunction by interfering with the structural brain network in SVD patients. The brain network measures may be regarded as direct and independent surrogate markers of cognitive impairment in SVD.

Details DOI

YNIMG Journal 2018 Journal Article

Generalized Recurrent Neural Network accommodating Dynamic Causal Modeling for functional MRI analysis

Yuan Wang
Yao Wang
Yvonne W. Lui

Dynamic Causal Modeling (DCM) is an advanced biophysical model which explicitly describes the entire process from experimental stimuli to functional magnetic resonance imaging (fMRI) signals via neural activity and cerebral hemodynamics. To conduct a DCM study, one needs to represent the experimental stimuli as a compact vector-valued function of time, which is hard in complex tasks such as book reading and natural movie watching. Deep learning provides the state-of-the-art signal representation solution, encoding complex signals into compact dense vectors while preserving the essence of the original signals. There is growing interest in using Recurrent Neural Networks (RNNs), a major family of deep learning techniques, in fMRI modeling. However, the generic RNNs used in existing studies work as black boxes, making the interpretation of results in a neuroscience context difficult and obscure. In this paper, we propose a new biophysically interpretable RNN built on DCM, DCM-RNN. We generalize the vanilla RNN and show that DCM can be cast faithfully as a special form of the generalized RNN. DCM-RNN uses back propagation for parameter estimation. We believe DCM-RNN is a promising tool for neuroscience. It can fit seamlessly into classical DCM studies. We demonstrate face validity of DCM-RNN in two principal applications of DCM: causal brain architecture hypotheses testing and effective connectivity estimation. We also demonstrate construct validity of DCM-RNN in an attention-visual experiment. Moreover, DCM-RNN enables end-to-end training of DCM and representation learning deep neural networks, extending DCM studies to complex tasks.

Details DOI