Author name cluster

Xingyu Wu

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.

16 papers

2 author rows

AAAI Conference 2025 Conference Paper

Collaborative Similarity Fusion and Consistency Recovery for Incomplete Multi-view Clustering

Bingbing Jiang
Chenglong Zhang
Xinyan Liang
Peng Zhou
Jie Yang
Xingyu Wu
Junyi Guan
Weiping Ding

As partial samples are often absent in certain views, incomplete multi-view clustering has become a challenging task. To tackle data with missing views, current methods either utilize the data similarity relations to recover missing samples or primarily consider the available information of existing samples, typically facing some inherent limitations. Firstly, traditional solutions cannot fully explore the potential information contained in missing samples due to their omission strategy, leading to sub-optimal graphs. Moreover, most methods mainly focus on data recovery from the view level, ignoring the differences among available/missing samples in various views. To this end, we propose a collaborative Similarity Fusion and Consistency Recovery (SFCR) method, which resolves the incomplete multi-view clustering problem by learning a unified similarity graph and recovering missing samples with consistent structures. Specifically, to learn a reliable graph compatible across views, a novel view-to-sample fusion model is designed to adaptively coalesce the view-wise similarities among available samples, not only preserving the complementarity and consistency among views but also properly balancing different samples. Furthermore, the missing samples are effectively recovered under the guidance of the fused similarity graph, so as to maintain the consistent structure of recovered data across views. In this way, the similarity learning and the missing data recovery benefit from each other in a collaborative reinforcement manner. Meanwhile, SFCR can directly obtain the final clustering labels without additional post-processing. Extensive experiments demonstrate the effectiveness and superiority of SFCR.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Design Principle Transfer in Neural Architecture Search via Large Language Models

Xun Zhou
Xingyu Wu
Liang Feng
Zhichao Lu
Kay Chen Tan

Transferable neural architecture search (TNAS) has been introduced to design efficient neural architectures for multiple tasks, to enhance the practical applicability of NAS in real-world scenarios. In TNAS, architectural knowledge accumulated in previous search processes is reused to warm up the architecture search for new tasks. However, existing TNAS methods still search in an extensive search space, necessitating the evaluation of numerous architectures. To overcome this challenge, this work proposes a novel transfer paradigm, i.e., design principle transfer. In this work, the linguistic description of various structural components' effects on architectural performance is termed design principles. They are learned from established architectures and then can be reused to reduce the search space tasks by discarding unpromising architectures. Searching in the refined search space can boost both the search performance and efficiency for new NAS tasks. To this end, a large language model (LLM)-assisted design principle transfer (LAPT) framework is devised. In LAPT, LLM is applied to automatically reason the design principles from a set of given architectures, and then a principle adaptation method is applied to refine these principles progressively based on the search results. Experimental results demonstrate that LAPT can beat the state-of-the-art TNAS methods on most tasks and achieve comparable performance on the remainder.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Diversity-Aware Policy Optimization for Large Language Model Reasoning

Jian Yao
Ran Cheng
Xingyu Wu
Jibin Wu
KC Tan

The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek-R1, which has inspired a surge of research into data quality and reinforcement learning (RL) algorithms. Despite the pivotal role diversity plays in RL, its influence on LLM reasoning remains largely underexplored. To bridge this gap, this work presents a systematic investigation into the impact of diversity in RL-based training for LLM reasoning, and proposes a novel diversity-aware policy optimization method. Across evaluations on 12 LLMs, we observe a strong positive correlation between the solution diversity and potential@k (a novel metric quantifying an LLM’s reasoning potential) in high-performing models. This finding motivates our method to explicitly promote diversity during RL training. Specifically, we design a token-level diversity and reformulate it into a practical objective, then we selectively apply it to positive samples. Integrated into the R1-zero training framework, our method achieves a 3. 5\% average improvement across four mathematical reasoning benchmarks, while generating more diverse and robust solutions.

PDF Details

EAAI Journal 2025 Journal Article

Event-triggered predefined-time tracking control for high-order nonlinear systems with time-varying actuator failures and uncertain disturbances

Yue Wang
Jie Gao
Junchan Zhao
Xingyu Wu

For a class of higher-order nonlinear system control problems with time-varying actuator failures and external disturbances, this paper designs efficient control strategies that allow the system to be stabilized in a predefined time. First, for such systems, this paper designs an effective predefined-time control strategy using the backstepping control method combined with the adaptive radial basis neural network technique, which makes the stabilization time of the system simple and adjustable. Secondly, while using the command filtering technique to solve the “complexity explosion” problem in the design of controllers for high-order nonlinear systems, this paper designs a novel predefined-time filtering error compensation mechanism to eliminate the impact of filtering errors on the stability of the system. Finally, an event-triggered mechanism is introduced, which effectively saves the communication resources. The effectiveness of the control strategy proposed in this paper is demonstrated by the simulation experiments.

Details DOI

IJCAI Conference 2025 Conference Paper

Gradient-based Causal Feature Selection

Zhaolong Ling
Mengxiang Guo
Xingyu Wu
Debo Cheng
Peng Zhou
Tianci Li
Zhangling Duan

Causal feature selection leverages causal discovery techniques to identify critical features associated with a target variable using observational data. Traditional methodologies primarily rely on constraint-based or score-based techniques, which are fraught with limitations. For example, conditional independence tests often yield unreliable results in the presence of noise and complex data generation processes, while the computational complexity of learning directed acyclic graphs increases exponentially with the number of variables involved. In light of recent advancements in deep learning, gradient-based methods have shown promise for global causal discovery. However, significant challenges arise when focusing on the identification of local causal features, particularly in defining the local causal constraint space to achieve both minimality and completeness. To address these issues, we introduce a novel gradient-based causal feature selection method (GCFS) that leverages an AutoEncoder to simultaneously model the target variable alongside other variables, thereby capturing of causal associations within a divide-and-conquer framework. Additionally, our approach incorporates a mask pruning strategy that transforms the search process into the minimization of a non-cyclic local reconstruction loss objective function. This function is then effectively optimized using a gradient-based method to accurately identify the causal features related to the target variable. Experimental results substantiate that GCFS surpasses existing methodologies across both synthetic and real datasets.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

Yu Zhou
Xingyu Wu
Jibin Wu
Liang Feng
KC Tan

Model merging is a technique that combines multiple large pretrained models into a single model, enhancing performance and broadening task adaptability without original data or additional training. However, most existing model merging methods focus primarily on exploring the parameter space, merging models with identical architectures. Despite its potential, merging in the architecture space remains in its early stages due to the vast search space and challenges related to layer compatibility. This paper designs a hierarchical model merging framework named HM3, formulating a bilevel multi-objective model merging problem across both parameter and architecture spaces. At the parameter level, HM3 integrates existing merging methods to quickly identify optimal parameters. Based on these, an actor-critic strategy with efficient policy discretization is employed at the architecture level to explore inference paths with Markov property in the layer-granularity search space for reconstructing these optimal models. By training reusable policy and value networks, HM3 learns Pareto optimal models to provide customized solutions for various tasks. Experimental results on language and vision tasks demonstrate that HM3 outperforms methods focusing solely on the parameter or architecture space.

PDF Details

IJCAI Conference 2025 Conference Paper

Hybrid Local Causal Discovery

Zhaolong Ling
Honghui Peng
Yiwen Zhang
Debo Cheng
Xingyu Wu
Peng Zhou
Kui Yu

Local causal discovery aims to identify and distinguish the direct causes and effects of a target variable from observational data. Due to the inherent incompleteness of local information, popular methods from global causal discovery often face new challenges in local causal discovery tasks, such as 1) erroneous symmetry constraint tests and the resulting cascading errors in constraint-based methods, and 2) confusion within score-based approaches caused by local spurious equivalence classes. To address the above issues, we propose a Hybrid Local Causal Discovery algorithm, called HLCD. Specifically, HLCD initially utilizes a constraint-based approach with the OR rule to obtain a candidate skeleton, which is subsequently refined using a score-based method to eliminate redundant structures. Furthermore, during the local causal orientation phase, HLCD distinguishes between V-structures and equivalence classes by comparing local structure scores between the two, thereby avoiding orientation interference caused by local equivalence class ambiguities. Comprehensive experiments on 14 benchmark Bayesian networks and two real datasets validate that the proposed algorithm outperforms the existing local causal discovery methods.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Local Causal Discovery Without Causal Sufficiency

Zhaolong Ling
Jiale Yu
Yiwen Zhang
Debo Cheng
Peng Zhou
Xingyu Wu
Bingbing Jiang
Kui Yu

Local causal discovery is crucial for revealing the causal relationships between specific variables from data. Existing local causal discovery algorithms are designed under the assumption of causal sufficiency, which states that there are no latent common causes for two or more of the observed variables in data. However, the assumption of causal sufficiency is often violated in practice. To address this issue, we first propose the local Maximal Ancestral Graph (MAG), referred to as LocalMAG, to describe the local causal relationships of the target variable in the MAG. Then, we propose a local causal discovery algorithm without the assumption of causal sufficiency, called LatentLCD, to learn the LocalMAG. Specifically, LatentLCD first uses the traditional parents and children discovery algorithm to identify the local causal skeleton that includes latent variables and verifies it theoretically. It then identifies bidirectional edges by determining whether both the target variable and its adjacent variables are colliders, thereby identifying latent variables in the local structure of the target variable. Extensive experiments on synthetic datasets have validated that the proposed LatentLCD algorithm significantly outperforms the state-of-the-art methods.

PDF Details DOI

ICML Conference 2025 Conference Paper

Towards Robustness and Explainability of Automatic Algorithm Selection

Xingyu Wu
Jibin Wu
Yu Zhou 0045
Liang Feng 0001
Kc Tan

Algorithm selection aims to identify the optimal performing algorithm before execution. Existing techniques typically focus on the observed correlations between algorithm performance and meta-features. However, little research has explored the underlying mechanisms of algorithm selection, specifically what characteristics an algorithm must possess to effectively tackle problems with certain feature values. This gap not only limits the explainability but also makes existing models vulnerable to data bias and distribution shift. This paper introduces directed acyclic graph (DAG) to describe this mechanism, proposing a novel modeling paradigm that aligns more closely with the fundamental logic of algorithm selection. By leveraging DAG to characterize the algorithm feature distribution conditioned on problem features, our approach enhances robustness against marginal distribution changes and allows for finer-grained predictions through the reconstruction of optimal algorithm features, with the final decision relying on differences between reconstructed and rejected algorithm features. Furthermore, we demonstrate that, the learned DAG and the proposed counterfactual calculations offer our approach with both model-level and instance-level explainability.

Details

ICML Conference 2024 Conference Paper

Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference

Yan Zhong 0001
Xingyu Wu
Li Zhang 0104
Chenxi Yang 0004
Tingting Jiang 0001

Due to the high cost of Image Quality Assessment (IQA) datasets, achieving robust generalization remains challenging for prevalent deep learning-based IQA methods. To address this, this paper proposes a novel end-to-end blind IQA method: Causal-IQA. Specifically, we first analyze the causal mechanisms in IQA tasks and construct a causal graph to understand the interplay and confounding effects between distortion types, image contents, and subjective human ratings. Then, through shifting the focus from correlations to causality, Causal-IQA aims to improve the estimation accuracy of image quality scores by mitigating the confounding effects using a causality-based optimization strategy. This optimization strategy is implemented on the sample subsets constructed by a Counterfactual Division process based on the Backdoor Criterion. Extensive experiments illustrate the superiority of Causal-IQA.

Details

IJCAI Conference 2024 Conference Paper

Efficient Multi-view Unsupervised Feature Selection with Adaptive Structure Learning and Inference

Chenglong Zhang
Yang Fang
Xinyan Liang
Han Zhang
Peng Zhou
Xingyu Wu
Jie Yang
Bingbing Jiang

As data with diverse representations become high-dimensional, multi-view unsupervised feature selection has been an important learning paradigm. Generally, existing methods encounter the following challenges: (i) traditional solutions either concatenate different views or introduce extra parameters to weight them, affecting the performance and applicability; (ii) emphasis is typically placed on graph construction, yet disregarding the clustering information of data; (iii) exploring the similarity structure of all samples from the original features is suboptimal and extremely time-consuming. To solve this dilemma, we propose an efficient multi-view unsupervised feature selection (EMUFS) to construct bipartite graphs between samples and anchors. Specifically, a parameter-free manner is devised to collaboratively fuse the membership matrices and graphs to learn the compatible structure information across all views, naturally balancing different views. Moreover, EMUFS leverages the similarity relations of data in the feature subspace induced by l2, 0-norm to dynamically update the graph. Accordingly, the cluster information of anchors can be accurately propagated to samples via the graph structure and further guide feature selection, enhancing the quality of selected features and the computational costs in solution processes. A convergent optimization is developed to solve the formulated problem, and experiments demonstrate the effectiveness and efficiency of EMUFS.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation

Xingyu Wu
Yan Zhong
Jibin Wu
Bingbing Jiang
Kay Chen Tan

Algorithm selection, a critical process of automated machine learning, aims to identify the most suitable algorithm for solving a specific problem prior to execution. Mainstream algorithm selection techniques heavily rely on problem features, while the role of algorithm features remains largely unexplored. Due to the intrinsic complexity of algorithms, effective methods for universally extracting algorithm information are lacking. This paper takes a significant step towards bridging this gap by introducing Large Language Models (LLMs) into algorithm selection for the first time. By comprehending the code text, LLM not only captures the structural and semantic aspects of the algorithm, but also demonstrates contextual awareness and library function understanding. The high-dimensional algorithm representation extracted by LLM, after undergoing a feature selection module, is combined with the problem representation and passed to the similarity calculation module. The selected algorithm is determined by the matching degree between a given problem and different algorithms. Extensive experiments validate the performance superiority of the proposed model and the efficacy of each key module. Furthermore, we present a theoretical upper bound on model complexity, showcasing the influence of algorithm representation and feature selection modules. This provides valuable theoretical guidance for the practical implementation of our method.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Practical Markov Boundary Learning without Strong Assumptions

Xingyu Wu
Bingbing Jiang
Tianhao Wu
Huanhuan Chen

Theoretically, the Markov boundary (MB) is the optimal solution for feature selection. However, existing MB learning algorithms often fail to identify some critical features in real-world feature selection tasks, mainly because the strict assumptions of existing algorithms, on either data distribution, variable types, or correctness of criteria, cannot be satisfied in application scenarios. This paper takes further steps toward opening the door to real-world applications for MB. We contribute in particular to a practical MB learning strategy, which can maintain feasibility and effectiveness in real-world data where variables can be numerical or categorical with linear or nonlinear, pairwise or multivariate relationships. Specifically, the equivalence between MB and the minimal conditional covariance operator (CCO) is investigated, which inspires us to design the objective function based on the predictability evaluation of the mapping variables in a reproducing kernel Hilbert space. Based on this, a kernel MB learning algorithm is proposed, where nonlinear multivariate dependence could be considered without extra requirements on data distribution and variable types. Extensive experiments demonstrate the efficacy of these contributions.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Generalization Bounds for Estimating Causal Effects of Continuous Treatments

Xin Wang
Shengfei Lyu
Xingyu Wu
Tianhao Wu
Huanhuan Chen

We focus on estimating causal effects of continuous treatments (e. g. , dosage in medicine), also known as dose-response function. Existing methods in causal inference for continuous treatments using neural networks are effective and to some extent reduce selection bias, which is introduced by non-randomized treatments among individuals and might lead to covariate imbalance and thus unreliable inference. To theoretically support the alleviation of selection bias in the setting of continuous treatments, we exploit the re-weighting schema and the Integral Probability Metric (IPM) distance to derive an upper bound on the counterfactual loss of estimating the average dose-response function (ADRF), and herein the IPM distance builds a bridge from a source (factual) domain to an infinite number of target (counterfactual) domains. We provide a discretized approximation of the IPM distance with a theoretical guarantee in the practical implementation. Based on the theoretical analyses, we also propose a novel algorithm, called Average Dose- response estiMatIon via re-weighTing schema (ADMIT). ADMIT simultaneously learns a re-weighting network, which aims to alleviate the selection bias, and an inference network, which makes factual and counterfactual estimations. In addition, the effectiveness of ADMIT is empirically demonstrated in both synthetic and semi-synthetic experiments by outperforming the existing benchmarks.

PDF Details

AAAI Conference 2020 Conference Paper

Multi-Label Causal Feature Selection

Xingyu Wu
Bingbing Jiang
Kui Yu
Huanhuan Chen
Chunyan Miao

Multi-label feature selection has received considerable attentions during the past decade. However, existing algorithms do not attempt to uncover the underlying causal mechanism, and individually solve different types of variable relationships, ignoring the mutual effects between them. Furthermore, these algorithms lack of interpretability, which can only select features for all labels, but cannot explain the correlation between a selected feature and a certain label. To address these problems, in this paper, we theoretically study the causal relationships in multi-label data, and propose a novel Markov blanket based multi-label causal feature selection (MB-MCF) algorithm. MB-MCF mines the causal mechanism of labels and features ﬁrst, to obtain a complete representation of information about labels. Based on the causal relationships, MB- MCF then selects predictive features and simultaneously distinguishes common features shared by multiple labels and label-speciﬁc features owned by single labels. Experiments on real-world data sets validate that MB-MCF could automatically determine the number of selected features and simultaneously achieve the best performance compared with state-of-the-art methods. An experiment in Emotions data set further demonstrates the interpretability of MB-MCF.

PDF Details

AAAI Conference 2019 Conference Paper

Joint Semi-Supervised Feature Selection and Classification through Bayesian Approach

Bingbing Jiang
Xingyu Wu
Kui Yu
Huanhuan Chen

With the increasing data dimensionality, feature selection has become a fundamental task to deal with high-dimensional data. Semi-supervised feature selection focuses on the problem of how to learn a relevant feature subset in the case of abundant unlabeled data with few labeled data. In recent years, many semi-supervised feature selection algorithms have been proposed. However, these algorithms are implemented by separating the processes of feature selection and classifier training, such that they cannot simultaneously select features and learn a classifier with the selected features. Moreover, they ignore the difference of reliability inside unlabeled samples and directly use them in the training stage, which might cause performance degradation. In this paper, we propose a joint semi-supervised feature selection and classification algorithm (JSFS) which adopts a Bayesian approach to automatically select the relevant features and simultaneously learn a classifier. Instead of using all unlabeled samples indiscriminately, JSFS associates each unlabeled sample with a self-adjusting weight to distinguish the difference between them, which can effectively eliminate the irrelevant unlabeled samples via introducing a left-truncated Gaussian prior. Experiments on various datasets demonstrate the effectiveness and superiority of JSFS.

PDF Details