Author name cluster

Xiaofang Zhou

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.

19 papers

1 author row

AAAI Conference 2026 Conference Paper

Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition

Yue Liu
Zhongying Ru
Shimin Di
Jipeng Zhang
Ruiyuan Zhang
Xiaofang Zhou

Retrieval-augment generation is a prevalent strategy to mitigate hallucinations of LLMs. The attributable RAG (RAGQ) generates quotes for its answers. The quotes indicate which input contexts support the RAG to derive the answers, enhancing the answer's verifiability and trustworthiness. However, existing RAGQs exhibit significant degradation when dealing with questions that require multi-hop reasoning and multi-modal understanding, suffering from over-citation, implicit entity identification failure, and poor generalization. In this paper, we propose a novel RAGQ framework, namely QDRAG. QDRAG breaks down the input question into atomic subquestions to identify the implicit entities. Then, the reranker prunes context distractors to eliminate the downstream over-citation. To facilitate query decomposition, we propose two zero-shot approaches: QD-C and QD-R, which guide the QD MLLM to decompose the question based on context knowledge and retrieval rewards, respectively. One interesting finding is that finetuning on the QD task shows better generalizability compared to directly finetuning on the downstream RAGQ task. Experiments on four multi-modal QA benchmarks demonstrate QDRAG's efficacy in grounding answers and generating faithful citations. The framework significantly outperforms all the baselines on both in-domain and out-of-domain tests, even surpassing Gemini-Pro.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Semantic-guided Diverse Decoding for Large Language Model

Weijie Shi
Yue Cui
Yaguang Wu
Jingzhi Fang
Shibo Zhang
Mengze Li
Sirui Han
Jia Zhu

Diverse decoding of large language models is crucial for applications requiring multiple semantically distinct responses, yet existing methods primarily achieve lexical rather than semantic diversity. This limitation significantly constrains Best-of-N strategies, group-based reinforcement learning, and data synthesis. While temperature sampling and diverse beam search modify token distributions or apply n-gram penalties, they fail to ensure meaningful semantic differentiation. We introduce Semantic-guided Diverse Decoding (SemDiD), operating directly in embedding space that balances quality with diversity through three complementary mechanisms: orthogonal directional guidance, dynamic inter-group repulsion, and position-debiased probability assessment. SemDiD harmonizes these competing objectives using adaptive gain functions and constraint optimization, ensuring both quality thresholds and maximal semantic differentiation. Experiments show SemDiD consistently outperforms existing methods, improving Best-of-N coverage by 1. 4-5. 2% across diverse tasks and accelerating RLHF training convergence by 15% while increasing accuracy by up to 2. 1%.

PDF Details

NeurIPS Conference 2024 Conference Paper

ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer

Jiawen Zhang
Shun Zheng
Xumeng Wen
Xiaofang Zhou
Jiang Bian
Jia Li

Numerous industrial sectors necessitate models capable of providing robust forecasts across various horizons. Despite the recent strides in crafting specific architectures for time-series forecasting and developing pre-trained universal models, a comprehensive examination of their capability in accommodating varied-horizon forecasting during inference is still lacking. This paper bridges this gap through the design and evaluation of the Elastic Time-Series Transformer (ElasTST). The ElasTST model incorporates a non-autoregressive design with placeholders and structured self-attention masks, warranting future outputs that are invariant to adjustments in inference horizons. A tunable version of rotary position embedding is also integrated into ElasTST to capture time-series-specific periods and enhance adaptability to different horizons. Additionally, ElasTST employs a multi-scale patch design, effectively integrating both fine-grained and coarse-grained information. During the training phase, ElasTST uses a horizon reweighting strategy that approximates the effect of random sampling across multiple horizons with a single fixed horizon setting. Through comprehensive experiments and comparisons with state-of-the-art time-series architectures and contemporary foundation models, we demonstrate the efficacy of ElasTST's unique design elements. Our findings position ElasTST as a robust solution for the practical necessity of varied-horizon forecasting.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Ensemble Semi-supervised Entity Alignment via Cycle-Teaching

Kexuan Xin
Zequn Sun
Wen Hua
Bing Liu
Wei Hu
Jianfeng Qu
Xiaofang Zhou

Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional semisupervised methods also suffer from the incorrect entity alignment in newly proposed training data. To resolve these issues, we design an iterative cycle-teaching framework for semisupervised entity alignment. The key idea is to train multiple entity alignment models (called aligners) simultaneously and let each aligner iteratively teach its successor the proposed new entity alignment. We propose a diversity-aware alignment selection method to choose reliable entity alignment for each aligner. We also design a conflict resolution mechanism to resolve the alignment conflict when combining the new alignment of an aligner and that from its teacher. Besides, considering the influence of cycle-teaching order, we elaborately design a strategy to arrange the optimal order that can maximize the overall performance of multiple aligners. The cycle-teaching process can break the limitations of each model’s learning capability and reduce the noise in new training data, leading to improved performance. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed cycle-teaching framework, which significantly outperforms the state-of-the-art models when the training data is insufficient and the new entity alignment has much noise.

PDF Details

TIST Journal 2022 Journal Article

Supply-Demand-aware Deep Reinforcement Learning for Dynamic Fleet Management

Bolong Zheng
Lingfeng Ming
Qi Hu
Zhipeng Lü
Guanfeng Liu
Xiaofang Zhou

Online ride-hailing platforms have reduced significantly the amounts of the time that taxis are idle and that passengers spend on waiting. As a key component of these platforms, the fleet management problem can be naturally modeled as a Markov Decision Process, which enables us to use the deep reinforcement learning. However, existing studies are proposed based on simplified problem settings that fail to model the complicated supply-dynamics and restrict the performance in the real traffic environment. In this article, we propose a supply-demand-aware deep reinforcement learning algorithm for taxi dispatching, where we use a deep Q-network with action sampling policy, called AS-DQN, to learn an optimal dispatching policy. Furthermore, we utilize a dueling network architecture, called AS-DDQN, to improve the performance of AS-DQN. Extensive experiments on real-world datasets offer insight into the performance of our model and show that it is capable of outperforming the baseline approaches.

Details DOI

IJCAI Conference 2021 Conference Paper

MFNP: A Meta-optimized Model for Few-shot Next POI Recommendation

Huimin Sun
Jiajie Xu
Kai Zheng
Pengpeng Zhao
Pingfu Chao
Xiaofang Zhou

Next Point-of-Interest (POI) recommendation is of great value for location-based services. Existing solutions mainly rely on extensive observed data and are brittle to users with few interactions. Unfortunately, the problem of few-shot next POI recommendation has not been well studied yet. In this paper, we propose a novel meta-optimized model MFNP, which can rapidly adapt to users with few check-in records. Towards the cold-start problem, it seamlessly integrates carefully designed user-specific and region-specific tasks in meta-learning, such that region-aware user preferences can be captured via a rational fusion of region-independent personal preferences and region-dependent crowd preferences. In modelling region-dependent crowd preferences, a cluster-based adaptive network is adopted to capture shared preferences from similar users for knowledge transfer. Experimental results on two real-world datasets show that our model outperforms the state-of-the-art methods on next POI recommendation for cold-start users.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Discovering Subsequence Patterns for Next POI Recommendation

Kangzhi Zhao
Yong Zhang
Hongzhi Yin
Jin Wang
Kai Zheng
Xiaofang Zhou
Chunxiao Xing

Next Point-of-Interest (POI) recommendation plays an important role in location-based services. State-of-the-art methods learn the POI-level sequential patterns in the user's check-in sequence but ignore the subsequence patterns that often represent the socio-economic activities or coherence of preference of the users. However, it is challenging to integrate the semantic subsequences due to the difficulty to predefine the granularity of the complex but meaningful subsequences. In this paper, we propose Adaptive Sequence Partitioner with Power-law Attention (ASPPA) to automatically identify each semantic subsequence of POIs and discover their sequential patterns. Our model adopts a state-based stacked recurrent neural network to hierarchically learn the latent structures of the user's check-in sequence. We also design a power-law attention mechanism to integrate the domain knowledge in spatial and temporal contexts. Extensive experiments on two real-world datasets demonstrate the effectiveness of our model.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Feature-level Deeper Self-Attention Network for Sequential Recommendation

Tingting Zhang
Pengpeng Zhao
Yanchi Liu
Victor S. Sheng
Jiajie Xu
Deqing Wang
Guanfeng Liu
Xiaofang Zhou

Sequential recommendation, which aims to recommend next item that the user will likely interact in a near future, has become essential in various Internet applications. Existing methods usually consider the transition patterns between items, but ignore the transition patterns between features of items. We argue that only the item-level sequences cannot reveal the full sequential patterns, while explicit and implicit feature-level sequences can help extract the full sequential patterns. In this paper, we propose a novel method named Feature-level Deeper Self-Attention Network (FDSA) for sequential recommendation. Specifically, FDSA first integrates various heterogeneous features of items into feature sequences with different weights through a vanilla mechanism. After that, FDSA applies separated self-attention blocks on item-level sequences and feature-level sequences, respectively, to model item transition patterns and feature transition patterns. Then, we integrate the outputs of these two blocks to a fully-connected layer for next item recommendation. Finally, comprehensive experimental results demonstrate that considering the transition relationships between features can significantly improve the performance of sequential recommendation.

PDF Details

IJCAI Conference 2019 Conference Paper

Graph Contextualized Self-Attention Network for Session-based Recommendation

Chengfeng Xu
Pengpeng Zhao
Yanchi Liu
Victor S. Sheng
Jiajie Xu
Fuzhen Zhuang
Junhua Fang
Xiaofang Zhou

Session-based recommendation, which aims to predict the user's immediate next action based on anonymous sessions, is a key task in many online services (e. g. , e-commerce, media streaming). Recently, Self-Attention Network (SAN) has achieved significant success in various sequence modeling tasks without using either recurrent or convolutional network. However, SAN lacks local dependencies that exist over adjacent items and limits its capacity for learning contextualized representations of items in sequences. In this paper, we propose a graph contextualized self-attention model (GC-SAN), which utilizes both graph neural network and self-attention mechanism, for session-based recommendation. In GC-SAN, we dynamically construct a graph structure for session sequences and capture rich local dependencies via graph neural network (GNN). Then each session learns long-range dependencies by applying the self-attention mechanism. Finally, each session is represented as a linear combination of the global preference and the current interest of that session. Extensive experiments on two real-world datasets show that GC-SAN outperforms state-of-the-art methods consistently.

PDF Details

AAAI Conference 2019 Conference Paper

Where to Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation

Pengpeng Zhao
Haifeng Zhu
Yanchi Liu
Jiajie Xu
Zhixu Li
Fuzhen Zhuang
Victor S. Sheng
Xiaofang Zhou

Next Point-of-Interest (POI) recommendation is of great value for both location-based service providers and users. However, the state-of-the-art Recurrent Neural Networks (RNNs) rarely consider the spatio-temporal intervals between neighbor check-ins, which are essential for modeling user check-in behaviors in next POI recommendation. To this end, in this paper, we propose a new Spatio-Temporal Gated Network (STGN) by enhancing long-short term memory network, where spatio-temporal gates are introduced to capture the spatio-temporal relationships between successive checkins. Specifically, two pairs of time gate and distance gate are designed to control the short-term interest and the longterm interest updates, respectively. Moreover, we introduce coupled input and forget gates to reduce the number of parameters and further improve efficiency. Finally, we evaluate the proposed model using four real-world datasets from various location-based social networks. The experimental results show that our model significantly outperforms the state-ofthe-art approaches for next POI recommendation.

PDF Details

IJCAI Conference 2018 Conference Paper

LC-RNN: A Deep Learning Model for Traffic Speed Prediction

Zhongjian Lv
Jiajie Xu
Kai Zheng
Hongzhi Yin
Pengpeng Zhao
Xiaofang Zhou

Traffic speed prediction is known as an important but challenging problem. In this paper, we propose a novel model, called LC-RNN, to achieve more accurate traffic speed prediction than existing solutions. It takes advantage of both RNN and CNN models by a rational integration of them, so as to learn more meaningful time-series patterns that can adapt to the traffic dynamics of surrounding areas. Furthermore, since traffic evolution is restricted by the underlying road network, a network embedded convolution structure is proposed to capture topology aware features. The fusion with other information, including periodicity and context factors, is also considered to further improve accuracy. Extensive experiments on two real datasets demonstrate that our proposed LC-RNN outperforms six well-known existing methods.

PDF Details

TIST Journal 2018 Journal Article

TPM

Weiqing Wang
Hongzhi Yin
Xingzhong Du
Quoc Viet Hung Nguyen
Xiaofang Zhou

With the rapid development of location-based social networks (LBSNs), spatial item recommendation has become an important way of helping users discover interesting locations to increase their engagement with location-based services. The availability of spatial, temporal, and social information in LBSNs offers an unprecedented opportunity to enhance the spatial item recommendation. Many previous works studied spatial and social influences on spatial item recommendation in LBSNs. Due to the strong correlations between a user’s check-in time and the corresponding check-in location, which include the sequential influence and temporal cyclic effect, it is essential for spatial item recommender system to exploit the temporal effect to improve the recommendation accuracy. Leveraging temporal information in spatial item recommendation is, however, very challenging, considering (1) when integrating sequential influences, users’ check-in data in LBSNs has a low sampling rate in both space and time, which renders existing location prediction techniques on GPS trajectories ineffective, and the prediction space is extremely large, with millions of distinct locations as the next prediction target, which impedes the application of classical Markov chain models; (2) there are various temporal cyclic patterns (i.e., daily, weekly, and monthly) in LBSNs, but existing work is limited to one specific pattern; and (3) there is no existing framework that unifies users’ personal interests, temporal cyclic patterns, and the sequential influence of recently visited locations in a principled manner. In light of the above challenges, we propose a Temporal Personalized Model ( TPM ), which introduces a novel latent variable topic-region to model and fuse sequential influence, cyclic patterns with personal interests in the latent and exponential space. The advantages of modeling the temporal effect at the topic-region level include a significantly reduced prediction space, an effective alleviation of data sparsity, and a direct expression of the semantic meaning of users’ spatial activities. Moreover, we introduce two methods to model the effect of various cyclic patterns. The first method is a time indexing scheme that encodes the effect of various cyclic patterns into a binary code. However, the indexing scheme faces the data sparsity problem in each time slice. To deal with this data sparsity problem, the second method slices the time according to each cyclic pattern separately and explores these patterns in a joint additive model. Furthermore, we design an asymmetric Locality Sensitive Hashing (ALSH) technique to speed up the online top- k recommendation process by extending the traditional LSH. We evaluate the performance of TPM on two real datasets and one large-scale synthetic dataset. The performance of TPM in recommending cold-start items is also evaluated. The results demonstrate a significant improvement in TPM’s ability to recommend spatial items, in terms of both effectiveness and efficiency, compared with the state-of-the-art methods.

Details DOI

TIST Journal 2017 Journal Article

ST-SAGE

Weiqing Wang
Hongzhi Yin
Ling Chen
Yizhou Sun
Shazia Sadiq
Xiaofang Zhou

With the rapid development of location-based social networks (LBSNs), spatial item recommendation has become an important mobile application, especially when users travel away from home. However, this type of recommendation is very challenging compared to traditional recommender systems. A user may visit only a limited number of spatial items, leading to a very sparse user-item matrix. This matrix becomes even sparser when the user travels to a distant place, as most of the items visited by a user are usually located within a short distance from the user’s home. Moreover, user interests and behavior patterns may vary dramatically across different time and geographical regions. In light of this, we propose ST-SAGE, a spatial-temporal sparse additive generative model for spatial item recommendation in this article. ST-SAGE considers both personal interests of the users and the preferences of the crowd in the target region at the given time by exploiting both the co-occurrence patterns and content of spatial items. To further alleviate the data-sparsity issue, ST-SAGE exploits the geographical correlation by smoothing the crowd’s preferences over a well-designed spatial index structure called the spatial pyramid. To speed up the training process of ST-SAGE, we implement a parallel version of the model inference algorithm on the GraphLab framework. We conduct extensive experiments; the experimental results clearly demonstrate that ST-SAGE outperforms the state-of-the-art recommender systems in terms of recommendation effectiveness, model training efficiency, and online recommendation efficiency.

Details DOI

TIST Journal 2016 Journal Article

A Spatial-Temporal Topic Model for the Semantic Annotation of POIs in LBSNs

Tieke He
Hongzhi Yin
Zhenyu Chen
Xiaofang Zhou
Shazia Sadiq
Bin Luo

Semantic tags of points of interest (POIs) are a crucial prerequisite for location search, recommendation services, and data cleaning. However, most POIs in location-based social networks (LBSNs) are either tag-missing or tag-incomplete. This article aims to develop semantic annotation techniques to automatically infer tags for POIs. We first analyze two LBSN datasets and observe that there are two types of tags, category-related ones and sentimental ones, which have unique characteristics. Category-related tags are hierarchical, whereas sentimental ones are category-aware. All existing related work has adopted classification methods to predict high-level category-related tags in the hierarchy, but they cannot apply to infer either low-level category tags or sentimental ones. In light of this, we propose a latent-class probabilistic generative model, namely the spatial-temporal topic model (STM), to infer personal interests, the temporal and spatial patterns of topics/semantics embedded in users’ check-in activities, the interdependence between category-topic and sentiment-topic, and the correlation between sentimental tags and rating scores from users’ check-in and rating behaviors. Then, this learned knowledge is utilized to automatically annotate all POIs with both category-related and sentimental tags in a unified way. We conduct extensive experiments to evaluate the performance of the proposed STM on a real large-scale dataset. The experimental results show the superiority of our proposed STM, and we also observe that the real challenge of inferring category-related tags for POIs lies in the low-level ones of the hierarchy and that the challenge of predicting sentimental tags are those with neutral ratings.

Details DOI

IJCAI Conference 2016 Conference Paper

Understanding Information Diffusion under Interactions

Yuan Su
Xi Zhang
Philip S. Yu
Wen Hua
Xiaofang Zhou
Binxing Fang

Information diffusion in online social networks has attracted substantial research effort. Although recent models begin to incorporate interactions among contagions, they still don't consider the comprehensive interactions involving users and contagions as a whole. Moreover, the interactions obtained in previous work are modeled as latent factors and thus are difficult to understand and interpret. In this paper, we investigate the contagion adoption behavior by incorporating various types of interactions into a coherent model, and propose a novel interaction-aware diffusion framework called IAD. IAD exploits the social network structures to distinguish user roles, and uses both structures and texts to categorize contagions. Experiments with large-scale Weibo dataset demonstrate that IAD outperforms the state-of-art baselines in terms of F1-score and accuracy, as well as the runtime for learning. In addition, the interactions obtained through learning reveal interesting findings, e. g. , food-related contagions have the strongest capability to suppress other contagions' propagation, while advertisement-related contagions have the weakest capability.

PDF Details

AAAI Conference 2015 Conference Paper

A Convex Formulation for Spectral Shrunk Clustering

Xiaojun Chang
Feiping Nie
Zhigang Ma
Yi Yang
Xiaofang Zhou

Spectral clustering is a fundamental technique in the field of data mining and information processing. Most existing spectral clustering algorithms integrate dimensionality reduction into the clustering process assisted by manifold learning in the original space. However, the manifold in reduced-dimensional subspace is likely to exhibit altered properties in contrast with the original space. Thus, applying manifold information obtained from the original space to the clustering process in a low-dimensional subspace is prone to inferior performance. Aiming to address this issue, we propose a novel convex algorithm that mines the manifold structure in the low-dimensional subspace. In addition, our unified learning process makes the manifold learning particularly tailored for the clustering. Compared with other related methods, the proposed algorithm results in more structured clustering result. To validate the efficacy of the proposed algorithm, we perform extensive experiments on several benchmark datasets in comparison with some state-of-the-art clustering approaches. The experimental results demonstrate that the proposed algorithm has quite promising clustering performance.

PDF Details

IJCAI Conference 2013 Conference Paper

Co-Regularized Ensemble for Feature Selection

Yahong Han
Yi Yang
Xiaofang Zhou

Supervised feature selection determines feature relevance by evaluating feature’s correlation with the classes. Joint minimization of a classifier’s loss function and an `2, 1-norm regularization has been shown to be effective for feature selection. However, the appropriate feature subset learned from different classifiers’ loss function may be different. Less effort has been made on improving the performance of feature selection by the ensemble of different classifiers’ criteria and take advantages of them. Furthermore, for the cases when only a few labeled data per class are available, overfitting would be a potential problem and the performance of each classifier is restrained. In this paper, we add a joint `2, 1-norm on multiple feature selection matrices to ensemble different classifiers’ loss function into a joint optimization framework. This added co-regularization term has twofold role in enhancing the effect of regularization for each criterion and uncovering common irrelevant features. The problem of over-fitting can be alleviated and thus the performance of feature selection is improved. Extensive experiment on different data types demonstrates the effectiveness of our algorithm.

PDF Details DOI

AAAI Conference 2012 Conference Paper

Unsupervised Feature Selection Using Nonnegative Spectral Analysis

Zechao Li
Yi Yang
Jing Liu
Xiaofang Zhou
Hanqing Lu

In this paper, a new unsupervised learning algorithm, namely Nonnegative Discriminative Feature Selection (NDFS), is proposed. To exploit the discriminative information in unsupervised scenarios, we perform spectral clustering to learn the cluster labels of the input samples, during which the feature selection is performed simultaneously. The joint learning of the cluster labels and feature selection matrix enables NDFS to select the most discriminative features. To learn more accurate cluster labels, a nonnegative constraint is explicitly imposed to the class indicators. To reduce the redundant or even noisy features, `2, 1-norm minimization constraint is added into the objective function, which guarantees the feature selection matrix sparse in rows. Our algorithm exploits the discriminative information and feature correlation simultaneously to select a better feature subset. A simple yet efficient iterative algorithm is designed to optimize the proposed objective function. Experimental results on different real world datasets demonstrate the encouraging performance of our algorithm over the state-of-the-arts.

PDF Details

AAAI Conference 2011 Conference Paper

Nonnegative Spectral Clustering with Discriminative Regularization

Yi Yang
Heng Shen
Feiping Nie
Rongrong Ji
Xiaofang Zhou

Clustering is a fundamental research topic in the ﬁeld of data mining. Optimizing the objective functions of clustering algorithms, e. g. normalized cut and k-means, is an NP-hard optimization problem. Existing algorithms usually relax the elements of cluster indicator matrix from discrete values to continuous ones. Eigenvalue decomposition is then performed to obtain a relaxed continuous solution, which must be discretized. The main problem is that the signs of the relaxed continuous solution are mixed. Such results may deviate severely from the true solution, making it a nontrivial task to get the cluster labels. To address the problem, we impose an explicit nonnegative constraint for a more accurate solution during the relaxation. Besides, we additionally introduce a discriminative regularization into the objective to avoid overﬁtting. A new iterative approach is proposed to optimize the objective. We show that the algorithm is a general one which naturally leads to other extensions. Experiments demonstrate the effectiveness of our algorithm.

PDF Details