Author name cluster

Xingwei 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.

18 papers

1 author row

AAAI Conference 2026 Conference Paper

MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation

Run Ling
Ke Cao
Jian Lu
Ao Ma
Haowei Liu
Runze He
Changwei Wang
Rongtao Xu

Multi-subject video generation aims to synthesize videos from textual prompts and multiple reference images, ensuring that each subject preserves natural scale and visual fidelity. However, current methods face two challenges: scale inconsistency, where variations in subject size lead to unnatural generation, and permutation sensitivity, where the order of reference inputs causes subject distortion. In this paper, we propose MoFu, a unified framework that tackles both challenges. For scale inconsistency, we introduce Scale-Aware Modulation (SMO), an LLM-guided module that extracts implicit scale cues from the prompt and modulates features to ensure consistent subject sizes. To address permutation sensitivity, we present a simple yet effective Fourier Fusion strategy that processes the frequency information of reference features via the Fast Fourier Transform to produce a unified representation. Besides, we design a Scale-Permutation Stability Loss to jointly encourage scale-consistent and permutation-invariant generation. To further evaluate these challenges, we establish a dedicated benchmark with controlled variations in subject scale and reference permutation. Extensive experiments demonstrate that MoFu significantly outperforms existing methods in preserving natural scale, subject fidelity, and overall visual quality.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation

Run Ling
Wenji Wang
Yuting Liu
Guibing Guo
Haowei Liu
Jian Lu
Quanwei Zhang
Yexing Xu

Personalized image generation is crucial for improving the user experience, as it renders reference images into preferred ones according to user visual preferences. Although effective, existing methods face two main issues. First, existing methods treat all items in the user's historical sequence equally when extracting user preferences, overlooking the varying semantic similarities between historical items and the reference item. Disproportionately high weights for low-similarity items distort user visual preferences for the reference item. Second, existing methods heavily rely on consistency between generated and reference images to optimize generation, which leads to underfitting user preferences and hinders personalization. To address these issues, we propose Retrieval Augmented Personalized Image GenerAtion guided by Recommendation (RAGAR). Our approach uses a retrieval mechanism to assign different weights to historical items according to their similarities to the reference item, thereby extracting more refined users' visual preferences for the reference item. Then we introduce a novel rank task based on the multi-modal ranking model to optimize the personalization of the generated images instead of forcing depend on consistency. Extensive experiments and human evaluations on three real-world datasets demonstrate that RAGAR achieves significant improvements in both personalization and semantic metrics compared to five baselines.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Self-Supervised Contrastive Re-Learning for Multi-Graph Multi-Label Classification

Meixia Wang
Yuhai Zhao
Zhengkui Wang
Yejiang Wang
Miaomiao Huang
Fenglong Ma
Fazal Wahab
Wen Shan

Multi-graph multi-label learning (MGML) represents each object as a bag-of-graphs with multiple labels, but demands large-scale labeled data whose acquisition is often difficult and costly. Self-supervised contrastive learning (SCL) mitigates label dependence by leveraging data augmentation to construct discriminative pretext tasks, proving effective for multi-instance learning. However, when applied to MGML, SCL faces two key challenges: (1) it distinguishes individual instances by their differences, whereas MGML requires modeling label correlations; (2) it assumes semantic invariance under augmentation, but structural perturbations in MGML alter label semantics. To tackle these challenges, we propose a self-suPervised contrastive rE-learning framework for mulTi-grAph multi-labeL classification (PETAL). Specifically, to model label correlations, we first define a unified label space to learn label prototypes and align features with them, yielding prototype-aligned representations. We then design a multi-granularity contrastive loss over these representations, which captures label dependencies by contrasting at the bag level, graph level, and bag-graph level. Moreover, to ensure semantic invariance, we develop a contrastive re-learning strategy based on prototype-aligned representations to generate augmentation-free positive samples. This guarantees consistent multi-label distributions without structural perturbations. Experiments on six datasets demonstrate that PETAL achieves an average improvement of 4.12% over state-of-the-art self-supervised and supervised baselines.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Augmenting Sequential Recommendation with Balanced Relevance and Diversity

Yizhou Dang
Jiahui Zhang
Yuting Liu
Enneng Yang
Yuliang Liang
Guibing Guo
Jianzhe Zhao
Xingwei Wang

By generating new yet effective data, data augmentation has become a promising method to mitigate the data sparsity problem in sequential recommendation. Existing works focus on augmenting the original data but rarely explore the issue of imbalanced relevance and diversity for augmented data, leading to semantic drift problems or limited performance improvements. In this paper, we propose a novel Balanced data Augmentation Plugin for Sequential Recommendation (BASRec) to generate data that balance relevance and diversity. BASRec consists of two modules: Single-sequence Augmentation and Cross-sequence Augmentation. The former leverages the randomness of the heuristic operators to generate diverse sequences for a single user, after which the diverse and the original sequences are fused at the representation level to obtain relevance. Further, we devise a reweighting strategy to enable the model to learn the preferences based on the two properties adaptively. The Cross-sequence Augmentation performs nonlinear mixing between different sequence representations from two directions. It produces virtual sequence representations that are diverse enough but retain the vital semantics of the original sequences. These two modules enhance the model to discover fine-grained preferences knowledge from single-user and cross-user perspectives. Extensive experiments verify the effectiveness of BASRec. The average improvement is up to 72.0% on GRU4Rec, 33.8% on SASRec, and 68.5% on FMLP-Rec. We demonstrate that BASRec generates data with a better balance between relevance and diversity than existing methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Coloring Learning for Heterophilic Graph Representation

Miaomiao Huang
Yuhai Zhao
Daniel Zhengkui Wang
Fenglong Ma
Yejiang Wang
Meixia Wang
Xingwei Wang

Graph self-supervised learning aims to learn the intrinsic graph representations from unlabeled data, with broad applicability in areas such as computing networks. Although graph contrastive learning (GCL) has achieved remarkable progress by generating perturbed views via data augmentation and optimizing sample similarity, it performs poorly in heterophilic graph scenarios (where connected nodes are likely to belong to different classes or exhibit dissimilar features). In heterophilic graphs, existing methods typically rely on random or carefully designed augmentation strategies (e. g. , edge dropping) for contrastive views. However, such graph structures exhibit intricate edge relationships, where topological perturbations may completely alter the semantics of neighborhoods. Moreover, most methods focus solely on local contrastive signals while neglecting global structural constraints. To address these limitations, inspired by graph coloring, we propose a novel Coloring learning for heterophilic graph Representation framework, CoRep, which: 1) Pioneers a coloring classifier to generate coloring labels, explicitly minimizing the discrepancy between homophilic nodes while maximizing that of heterophilic nodes. A global positive sample set is constructed using multi-hop same-color nodes to capture global semantic consistency. 2) Introduces a learnable edge evaluator to guide the coloring learning dynamically and utilizes the edges' triplet relations to enhance its robustness. 3) Leverages Gumbel-Softmax to differentially discretize color distributions, suppressing noise via a redundancy constraint and enhancing intra-class compactness. Experimental results on 14 benchmark datasets demonstrate that CoRep significantly outperforms current state-of-the-art methods.

PDF Details

NeurIPS Conference 2025 Conference Paper

Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity

Enneng Yang
Anke Tang
Li Shen
Guibing Guo
Xingwei Wang
Xiaochun Cao
Jie Zhang

Model merging integrates multiple expert models with diverse capabilities into a unified framework, facilitating collaborative learning. However, most existing methods assume simultaneous access to all models, which is often impractical in real-world scenarios where models are received sequentially. While some studies have investigated continual model merging (CMM)--which involves sequentially merging multiple models--the challenge of balancing prior knowledge (stability) and incorporating new tasks (plasticity) remains unresolved. This paper, for the first time, formally defines the stability and plasticity of CMM from the perspective of orthogonal projection. Subsequently, we analyze the relationships among the spaces spanned by task data, historical gradients, and accumulated gradients. Building on this, we propose a data-free \textbf{D}ual \textbf{O}rthogonal \textbf{P}rojection (DOP) method, which eliminates data dependence and mitigates interference between the merged model and models for old and new tasks by projecting their parameter differences onto their respective approximate data spaces. Finally, to solve potential conflicts between stability and plasticity, we reformulate DOP as a multi-objective optimization problem and employ a multi-gradient descent algorithm to obtain a Pareto-optimal solution. Extensive experiments across multiple architectures and task configurations validate that our approach significantly outperforms state-of-the-art CMM methods.

PDF Details

AAAI Conference 2025 Conference Paper

CoRA: Collaborative Information Perception by Large Language Model’s Weights for Recommendation

Yuting Liu
Jinghao Zhang
Yizhou Dang
Yuliang Liang
Qiang Liu
Guibing Guo
Jianzhe Zhao
Xingwei Wang

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified sequence input and then fine-tuning to align these features with LLM's input space. Although effective, in this work, we identify two limitations when adapting LLMs to recommendation tasks, which hinder the integration of general knowledge and collaborative information, resulting in sub-optimal recommendation performance. (1) Fine-tuning LLM with recommendation data can undermine its inherent world knowledge and fundamental competencies, which are crucial for interpreting and inferring recommendation text. (2) Incorporating collaborative features into textual prompts disrupts the semantics of the original prompts, preventing LLM from generating appropriate outputs. In this paper, we propose a new paradigm, Collaborative LoRA (CoRA), with a collaborative query generator. Rather than input space alignment, this method aligns collaborative information with LLM's parameter space, representing them as incremental weights to update LLM's output. This way, LLM perceives collaborative information without altering its general knowledge and text inference capabilities. Specifically, we employ a collaborative filtering model to extract user and item embeddings and inject them into a set number of learnable queries. We then convert collaborative queries into collaborative weights with low-rank properties and merge the collaborative weights into LLM's weights, enabling LLM to perceive the collaborative signals and generate personalized recommendations without fine-tuning or extra collaborative tokens in prompts. Extensive experiments confirm that CoRA effectively integrates collaborative information into LLM, enhancing recommendation performance.

PDF Details DOI

AAAI Conference 2025 Conference Paper

EPT: Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion

Pengxiang Lan
Enneng Yang
Yuting Liu
Guibing Guo
Jianzhe Zhao
Xingwei Wang

Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely learning the embeddings of prompt tokens. Nevertheless, existing methods still suffer from two challenges: (i) they are hard to balance accuracy and efficiency. A longer (shorter) soft prompt generally leads to a better (worse) accuracy but at the cost of more (less) training time. (ii) The performance may not be consistent when adapting to different downstream tasks. We attribute it to the same embedding space but responsible for different requirements of downstream tasks. To address these issues, we propose an Efficient Prompt Tuning method (EPT) by multi-space projection and prompt fusion. Specifically, it decomposes a given soft prompt into a shorter prompt and two low-rank matrices, significantly reducing the training time. Accuracy is also enhanced by leveraging low-rank matrices and the short prompt as additional knowledge sources to enrich the semantics of the original short prompt. In addition, we project the soft prompt into multiple subspaces to improve the performance consistency, and then adaptively learn the combination weights of different spaces through a gating network. Experiments on 13 natural language processing downstream tasks show that our method significantly and consistently outperforms 11 comparison methods with the relative percentage of improvements up to 12.9%, and training time decreased by 14%.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Multiple Purchase Chains with Negative Transfer Elimination for Multi-Behavior Recommendation

Shuwei Gong
Yuting Liu
Yizhou Dang
Guibing Guo
Jianzhe Zhao
Xingwei Wang

Multi-behavior recommendation exploits auxiliary behaviors (e.g., view, cart) to help predict users' potential target behavior (e.g., purchase) on a given item. However, existing works suffer from two issues: (1) They generally consider only a single chain from auxiliary behaviors to the target behavior, referred to as a purchase chain (e.g., view -> cart -> purchase), ignoring other valuable purchase chains (e.g., view ->purchase) that are beneficial for recommendation performance. (2) Most studies presume that interacted items in auxiliary behaviors are good for recommendations, and pay little attention to the negative transfer problem. That is, some auxiliary behaviors may negatively transfer the influence to the modeling of target ones (e.g., items viewed but not purchased). To alleviate these issues, we propose a novel Multiple Purchase Chains (MPC) model with negative transfer elimination for multi-behavior recommendation. Specifically, we construct multiple purchase chains from auxiliary to target behaviors according to users' historical interactions, while the representations of a previous behavior will be fed to initialize the next behavior on the chain. Then, we construct a negative graph for the latter behavior and learn the negative representations of users and items which will be filtered out to eliminate negative transfer. Experimental results on two real datasets outperform the best baseline by 40.97% and 47.26% on average in terms of Recall@10 and NDCG@10 respectively, demonstrating the effectiveness of our method.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Limited-Supervised Multi-Label Learning with Dependency Noise

Yejiang Wang
Yuhai Zhao
Zhengkui Wang
Wen Shan
Xingwei Wang

Limited-supervised multi-label learning (LML) leverages weak or noisy supervision for multi-label classification model training over data with label noise, which contain missing labels and/or redundant labels. Existing studies usually solve LML problems by assuming that label noise is independent of the input features and class labels, while ignoring the fact that noisy labels may depend on the input features (instance-dependent) and the classes (label-dependent) in many real-world applications. In this paper, we propose limited-supervised Multi-label Learning with Dependency Noise (MLDN) to simultaneously identify the instance-dependent and label-dependent label noise by factorizing the noise matrix as the outputs of a mapping from the feature and label representations. Meanwhile, we regularize the problem with the manifold constraint on noise matrix to preserve local relationships and uncover the manifold structure. Theoretically, we bound noise recover error for the resulting problem. We solve the problem by using a first-order scheme based on proximal operator, and the convergence rate of it is at least sub-linear. Extensive experiments conducted on various datasets demonstrate the superiority of our proposed method.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Towards Robust Multi-Label Learning against Dirty Label Noise

Yuhai Zhao
Yejiang Wang
Zhengkui Wang
Wen Shan
Miaomiao Huang
Meixia Wang
Min Huang
Xingwei Wang

In multi-label learning, one of the major challenges is that the data are associated with label noise including the random noisy labels (e. g. , data encoding errors) and noisy labels created by annotators (e. g. , missing, extra, or error label), where noise is promoted by different structures (e. g. , gaussian, sparse or subjective). Existing methods are tailored to handle noise with one specific structure. However, they lack of consideration of the fact that the data are always with dirty noisy labels, simutaneously gaussian, sparse and subjective, in real applications. In this paper, we formalize the multi-label learning with dirty noise as a new learning problem, namely Noisy Multi-label Learning (NML). To solve the NML problem, we decompose a corrupted label matrix as the noise matrix plus a true label matrix (maybe high-rank). For the noise matrix, a mixed norm penalty is developed as regularizer for dirty noise distribution. Under this norm, the conditions required for exact noise recovery are provided theoretically. For the true label matrix that is not necessarily low-rank, we apply a non-linear mapping to ensure its low-rankness such that the high-order label correlation can be utilized. Experimental results show that the proposed method outperforms the state-of-the-art methods significantly.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Basket Representation Learning by Hypergraph Convolution on Repeated Items for Next-basket Recommendation

Yalin Yu
Enneng Yang
Guibing Guo
Linying Jiang
Xingwei Wang

Basket representation plays an important role in the task of next-basket recommendation. However, existing methods generally adopts pooling operations to learn a basket's representation, from which two critical issues can be identified. First, they treat a basket as a set of items independent and identically distributed. We find that items occurring in the same basket have much higher correlations than those randomly selected by conducting data analysis on a real dataset. Second, although some works have recognized the importance of items repeatedly purchased in multiple baskets, they ignore the correlations among the repeated items in a same basket, whose importance is shown by our data analysis. In this paper, we propose a novel Basket Representation Learning (BRL) model by leveraging the correlations among intra-basket items. Specifically, we first connect all the items (in a basket) as a hyperedge, where the correlations among different items can be well exploited by hypergraph convolution operations. Meanwhile, we also connect all the repeated items in the same basket as a hyperedge, whereby their correlations can be further strengthened. We generate a negative (positive) view of the basket by data augmentation on repeated (non-repeated) items, and apply contrastive learning to force more agreements on repeated items. Finally, experimental results on three real datasets show that our approach performs better than eight baselines in ranking accuracy.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation

Yizhou Dang
Enneng Yang
Guibing Guo
Linying Jiang
Xingwei Wang
Xiaoxiao Xu
Qinghui Sun
Hong Liu

Sequential recommendation is an important task to predict the next-item to access based on a sequence of interacted items. Most existing works learn user preference as the transition pattern from the previous item to the next one, ignoring the time interval between these two items. However, we observe that the time interval in a sequence may vary significantly different, and thus result in the ineffectiveness of user modeling due to the issue of preference drift. In fact, we conducted an empirical study to validate this observation, and found that a sequence with uniformly distributed time interval (denoted as uniform sequence) is more beneficial for performance improvement than that with greatly varying time interval. Therefore, we propose to augment sequence data from the perspective of time interval, which is not studied in the literature. Specifically, we design five operators (Ti-Crop, Ti-Reorder, Ti-Mask, Ti-Substitute, Ti-Insert) to transform the original non-uniform sequence to uniform sequence with the consideration of variance of time intervals. Then, we devise a control strategy to execute data augmentation on item sequences in different lengths. Finally, we implement these improvements on a state-of-the-art model CoSeRec and validate our approach on four real datasets. The experimental results show that our approach reaches significantly better performance than the other 9 competing methods. Our implementation is available: https://github.com/KingGugu/TiCoSeRec.

PDF Details DOI

IS Journal 2021 Journal Article

VSE-fs: Fast Full-Sample Visual Semantic Embedding

Songlin Zhai
Guibing Guo
Fajie Yuan
Yuan Liu
Xingwei Wang

The visual semantic embedding (VSE) aims to construct a joint embedding space between visual features and semantic information, whereby classes can be well retrieved for a given image. However, VSE faces the computational challenge due to the large scale image-class data and the constrained system processing power. To speed up model training, many researchers resort to different sampling strategies by involving only a small portion of the classes at each training step. However, these methods are greatly biased especially when the sampling distribution deviates from the true data distribution. In order to retain VSE models fidelity, we adopt the regular full-sample in our algorithm. We also devise two separate optimization strategies to reduce time complexity, and derive more effective updating rules. The experimental results on four real datasets demonstrate that our approach not only converges much faster than the state-of-the-art sampling models, but also generates more accurate class retrieval.

Details DOI

EAAI Journal 2018 Journal Article

A systematic model of stable multilateral automated negotiation in e-market environment

Taiguang Gao
Min Huang
Qing Wang
Mingqiang Yin
Wai Ki Ching
Loo Hay Lee
Xingwei Wang

In e-market environment, the participants are usually bilateral such as in Consumer-to-Business or Customer-to-Customer business models. The participant on each side prefers the counterpart from which the concerned issues or profits can be pursued. Hence, the effective matching from a global point of view and the stable matching from an individual point of view become the critical function of the business models. In this paper, a systematic model of Stable Multilateral Automated Negotiation (SMAN) is proposed to facilitate the involved parties’ matching process in two-sided e-market, where confidential mediator agent as well as party agents communicate and make decisions on behalf of their principal parties. To make the matching effective and stable, two optimization models are designed. One is matching points model which makes an effective balance among the proposal value of issues for each possible pair of matching, such that the joint weighted profit measure is optimized with feature rescaling. The other one is matching scheme model which optimizes Social Welfare (SW) subject to the stable constraints, and ensures the engaged individual party satisfies the matching result from its viewpoint. And the optimality of stable matching is proved by mathematical deduction. Finally, numerical experiments are illustrated and show that the designed systematic models can generate effective matchings with individually stable advantages over the traditional Multilateral Automated Negotiation of Two Sides (MANTS).

Details DOI

IJCAI Conference 2018 Conference Paper

Approximating Word Ranking and Negative Sampling for Word Embedding

Guibing Guo
Shichang Ouyang
Fajie Yuan
Xingwei Wang

CBOW (Continuous Bag-Of-Words) is one of the most commonly used techniques to generate word embeddings in various NLP tasks. However, it fails to reach the optimal performance due to uniform involvements of positive words and a simple sampling distribution of negative words. To resolve these issues, we propose OptRank to optimize word ranking and approximate negative sampling for bettering word embedding. Specifically, we first formalize word embedding as a ranking problem. Then, we weigh the positive words by their ranks such that highly ranked words have more importance, and adopt a dynamic sampling strategy to select informative negative words. In addition, an approximation method is designed to efficiently compute word ranks. Empirical experiments show that OptRank consistently outperforms its counterparts on a benchmark dataset with different sampling scales, especially when the sampled subset is small. The code and datasets can be obtained from https: //github. com/ouououououou/OptRank.

PDF Details

AAAI Conference 2018 Conference Paper

VSE-ens: Visual-Semantic Embeddings with Efficient Negative Sampling

Guibing Guo
Songlin Zhai
Fajie Yuan
Yuan Liu
Xingwei Wang

Jointing visual-semantic embeddings (VSE) have become a research hotpot for the task of image annotation, which suffers from the issue of semantic gap, i. e. , the gap between images’ visual features (low-level) and labels’ semantic features (high-level). This issue will be even more challenging if visual features cannot be retrieved from images, that is, when images are only denoted by numerical IDs as given in some real datasets. The typical way of existing VSE methods is to perform a uniform sampling method for negative examples that violate the ranking order against positive examples, which requires a time-consuming search in the whole label space. In this paper, we propose a fast adaptive negative sampler that can work well in the settings of no ﬁgure pixels available. Our sampling strategy is to choose the negative examples that are most likely to meet the requirements of violation according to the latent factors of images. In this way, our approach can linearly scale up to large datasets. The experiments demonstrate that our approach converges 5. 02x faster than the state-of-the-art approaches on OpenImages, 2. 5x on IAPR-TCI2 and 2. 06x on NUS-WIDE datasets, as well as better ranking accuracy across datasets.

PDF Details

EAAI Journal 2013 Journal Article

Multi-robot navigation based QoS routing in self-organizing networks

Xingwei Wang
Hui Cheng
Min Huang

The technical development drives the future networks to become large-scale, heterogeneous, and dynamic. Bio-inspired networking can help reduce the time-space complexity of the complex network. Due to the good features such as self-organization and self-management, self-organizing network (SON) will most probably be a priority choice for the next generation network. In this paper, a swarm intelligence based Quality of Service (QoS) routing protocol is proposed for SON. The inaccurate routing and QoS information is described with fuzzy mathematics whilst the utilities of both the user and the network service provider are considered by applying game theory. Based on the multi-robot navigation algorithm, the protocol is able to search a routing path which can satisfy the user QoS requirements and achieve the Pareto optimal utilities of the user and the network service provider under Nash equilibrium. The proposed protocol is implemented and evaluated by extensive simulation experiments. The results show that it beats both other swarm intelligence based routing protocols and the traditional Dijkstra algorithm based routing protocol. The searched routing paths support the win–win effect for both the user and the network service provider.

Details DOI