XLXueying Li

Xueying Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xueying Li has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Batch-Adaptive Doubly Robust Learning for Debiasing Post-Click Conversion Rate Prediction Under Sparse Data

    by Hang Pan, Chunyuan Zheng, Wenjie Wang, Jingang Jiang, Xueying Li, Haoxuan Li, Fuli Feng

    Post-Click Conversion Rate (CVR) prediction aims to predict the probability of a conversion event occurring after a user clicks. Most CVR prediction methods use clicked events to train models and subsequently predict on both clicked and unclicked events, facing selection bias. To unbiasedly predict CVR, doubly robust (DR) learning incorporates propensity score reweighting and missing data error imputation, but with suboptimal performance under sparse click events. We theoretically demonstrate that existing DR methods face high or even unbounded bias, variance, and generalization error bound under small propensity scores from sparse click events. This motivates us to propose a new Batch-Adaptive DR (BADR) Learning method. In particular, we propose a BADR estimator, which adaptively adjusts the influence of each data batch during debiasing CVR prediction model training based on the propensity scores within that batch. We prove that the BADR estimator has bounded bias, variance, and generalization error bound, all of which are smaller than those of the DR estimator under small propensity scores, while maintaining asymptotic double robustness, i.e., achieving double robustness under a large sample size. Furthermore, we approximate the variance of the BADR estimator and derive a new batch-adaptive imputation model training loss compatible with the BADR estimator, which theoretically ensures further variance reduction during training. Our experiments on real-world datasets validate BADR’s effectiveness and rationality.


  • Top Cited Papers
    Open Access

    DynLLM: When Large Language Models Meet Dynamic Graph-based Recommendation

    by Ziwei Zhao, Fake Lin, Xi Zhu, Zhi Zheng, Tong Xu, Shitian Shen, Xueying Li, Zikai Yin, Enhong Chen

    Recommendation systems have become ubiquitous tools in online platforms, providing personalized suggestions based on user–item interactions. To capture the dynamic higher-order connections between users and items, recommendation approaches based on dynamic graphs have garnered significant attention from researchers. However, existing recommendation methods based on dynamic graphs are often limited by data sparsity, which prevents them from achieving satisfactory performance. Fortunately, the rapid development of large language models (LLMs) with powerful text generation capabilities and extensive domain knowledge has offered new possibilities for addressing this challenge. However, how to effectively integrate LLMs with dynamic graphs remains unexplored. To bridge this gap, in this article, we propose a novel framework, that is, DynLLM, for applying LLMs to dynamic graph-based recommendation methods. Specifically, DynLLM harnesses the power of LLMs to generate multi-faceted user profiles based on the rich textual features of historical purchase records, which in turn supplement and enrich the underlying relationships between users and items. Along this line, to fuse the multi-faceted profiles with temporal graph embedding, we engage LLMs to derive corresponding profile embeddings and further employ a distilled attention mechanism to refine the LLM-generated profile embeddings for alleviating noisy signals, while also assessing and adjusting the relevance of each distilled facet embedding for seamless integration with temporal graph embedding from continuous time dynamic graphs (CTDGs). Extensive experiments on three real datasets have validated the superior improvements of DynLLM over a wide range of state-of-the-art baseline methods. The implementation code is available online at https://github.com/meteor-gif/DynLLM .


  • Open Access

    Knowledge Graph Pruning for Recommendation

    by Fake Lin, Xi Zhu, Ziwei Zhao, Deqiang Huang, Yu Yu, Xueying Li, Zhi Zheng, Tong Xu, Enhong Chen

    Recent years have witnessed the prosperity of Knowledge Graph-Based Recommendation System (KGRS), which enriches the representation of users, items, and entities by structural knowledge with striking improvement. Nevertheless, its unaffordable computational cost still limits researchers from exploring more sophisticated models. We observe that the bottleneck for training efficiency arises from the knowledge graph, which is plagued by the well-known issue of knowledge explosion. Recently, some works have attempted to slim the inflated KG via summarization techniques, which summarize multiple real nodes into the single virtual one. However, these summarized virtual nodes may ignore collaborative signals and thus fail to figure out the redundant nodes related to recommendation task. To this end, in this article, we propose a novel approach called KGTrimmer for knowledge graph pruning tailored for recommendation, to remove the unessential nodes while minimizing performance degradation. Specifically, we design an importance evaluator from a dual-view perspective. For the collective view, we embrace the idea of collective intelligence by extracting community consensus based on abundant collaborative signals, i.e., nodes are considered important if they attract attention of numerous users. For the holistic view, we learn a global mask to identify the valueless nodes from their inherent properties or overall popularity. With the collective and holistic importance scores, we build an end-to-end importance-aware graph neural network, which injects filtered knowledge to enhance the distillation of valuable user-item collaborative signals. Ultimately, we generate a pruned knowledge graph with lightweight, stable, and robust properties to facilitate the following-up recommendation task. Extensive experiments are conducted on three publicly available datasets to prove the effectiveness and generalizability of KGTrimmer, where it can reduce the number of triplets in KG by up to 90% without compromising performance.


  • Open Access

    Multi-Behavior Recommendation with Personalized Directed Acyclic Behavior Graphs

    by Xi Zhu, Fake Lin, Ziwei Zhao, Tong Xu, Xiangyu Zhao, Zikai Yin, Xueying Li, Enhong Chen

    A well-developed recommendation system can not only leverage multi-typed interactions (such as page view , add-to-cart , and purchase ) to better identify user preferences but also demonstrate high performance, low complexity, and strong interpretability. However, many existing solutions for multi-behavior recommendation fall short of intuitive modeling of real-world scenarios, leading to overly complex models with massive parameters and cumbersome components. In particular, they share two critical limitations: (1) Some pioneering models are built upon the strict assumption of cascade effects across behaviors, which contradicts multifarious behavior paths in practical applications. (2) Existing approaches fail to explicitly capture the unique idiosyncrasies of users and even neglect the inherent nature of items involved in the multi-behavior interactions. To this end, we propose a novel Directed Acyclic Graph Convolutional Network (DA-GCN) for the multi-behavior recommendation task. Specifically, we pinpoint the partial order relations within the monotonic behavior chain and extend it to personalized directed acyclic behavior graphs to exploit behavior dependencies. Then, a GCN-based directed edge encoder is employed to distill rich collaborative signals embodied by each directed edge. In light of the information flows over the directed acyclic structure, we propose an attentive aggregation module to gather messages from all potential antecedent behaviors, representing distinct perspectives to understand the terminated behavior. Thus, we obtain comprehensive representations for the follow-up behavior through learnable distributions over its preceding behaviors, explicitly reflecting personalized interactive patterns of users and underlying properties of items simultaneously. Finally, we design a customized multi-task learning objective for flexible joint optimization. Extensive experiments on public benchmarking datasets fully demonstrate the superiority of DA-GCN with significant performance improvement and computational efficiency over a wide range of state-of-the-art methods. Our code is available at https://github.com/xizhu1022/DA-GCN .


  • Open Access

    When Box Meets Graph Neural Network in Tag-aware Recommendation

    by Fake Lin, Ziwei Zhao, Xi Zhu, Da Zhang, Shitian Shen, Xueying Li, Tong Xu, Suojuan Zhang, Enhong Chen

    Last year has witnessed the re-flourishment of tag-aware recommender systems supported by the LLM-enriched tags. Unfortunately, though large efforts have been made, current solutions may fail to describe the diversity and uncertainty inherent in user preferences with only tag-driven profiles. Recently, with the development of geometry-based techniques, e.g., box embeddings, the diversity of user preferences now could be fully modeled as the range within a box in high dimension space. However, defect still exists as these approaches are incapable of capturing high-order neighbor signals, i.e., semantic-rich multi-hop relations within the user-tag-item tripartite graph, which severely limits the effectiveness of user modeling. To deal with this challenge, in this paper, we propose a novel framework, called BoxGNN, to perform message aggregation via combinations of logical operations, thereby incorporating high-order signals. Specifically, we first embed users, items, and tags as hyper-boxes rather than simple points in the representation space, and define two logical operations, i.e., union and intersection, to facilitate the subsequent process. Next, we perform the message aggregation mechanism via the combination of logical operations, to obtain the corresponding high-order box representations. Finally, we adopt a volume-based learning objective with Gumbel smoothing techniques to refine the representation of boxes. Extensive experiments on two publicly available datasets and one LLM-enhanced e-commerce dataset have validated the superiority of BoxGNN compared with various state-of-the-art baselines. The code is released online: https://github.com/critical88/BoxGNN.


  • Adversarial Attack and Defense on Discrete Time Dynamic Graphs

    by Ziwei Zhao, Yu Yang, Zikai Yin, Tong Xu, Xi Zhu, Fake Lin, Xueying Li, Enhong Chen

    Graph learning methods have achieved remarkable performance in various domains such as social recommendation, financial fraud detection, and so on. In real applications, the underlying graph is often dynamically evolving and thus, some recent studies focus on integrating the temporal topology information of graphs into the GNN for learning graph embedding. However, the robustness of training GNNs for dynamic graphs has not been discussed so far. The major reason is how to attack dynamic graph embedding still remains largely untouched, let alone how to defend against the attacks. To enable robust training of GNNs for dynamic graphs, in this paper, we investigate the problem of how to generate attacks and defend against attacks for dynamic graph embedding. Attacking dynamic graph embedding is more challenging than attacking static graph embedding as we need to understand the temporal dynamics of graphs as well as its impact on the embedding and the injected perturbations should be distinguished from the natural evolution. In addition, the defense is very challenging as the perturbations may be hidden within the natural evolution. To tackle these technical challenges, in this paper, we first develop a novel gradient-based attack method from an optimization perspective to generate perturbations to fool dynamic graph learning methods, where a key idea is to use gradient dynamics to attack the natural dynamics of the graph. Further, we borrow the idea of the attack method and integrate it with adversarial training to train a more robust dynamic graph learning method to defend against hand-crafted attacks. Finally, extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed attack and defense method, where our defense method not only achieves comparable performance on clean graphs but also significantly increases the defense performance on attacked graphs.


  • Open Access

    Time-interval Aware Share Recommendation via Bi-directional Continuous Time Dynamic Graphs

    by Ziwei Zhao, Xi Zhu, Tong Xu, Aakas Lizhiyu, Yu Yu, Xueying Li, Zikai Yin, Enhong Chen


  • Open Access

    Streaming Algorithms for Constrained Submodular Maximization

    by Shuang Cui, Kai Han, Jing Tang, He Huang, Xueying Li, Zhiyu Li

    Due to the pervasive "diminishing returns" property appeared in data-intensive applications, submodular maximization problems have aroused great attention from both the machine learning community and the computation theory community. During the last decades, a lot of algorithms have been proposed for submodular maximization subject to various constraints [4, 6, 8], and these algorithms can be used in numerous applications including sensor placement [9], clustering [5], network design [13], and so on. The existing algorithms for submodular maximization can be roughly classified into offline algorithms and streaming algorithms; the former assume full access to the whole dataset at any time (e.g.,[4, 10]), while the latter only require an amount of space which is nearly linear in the maximum size of a feasible solution (e.g., [1, 7]). Apparently, streaming algorithms are more useful in big data applications, as the whole data set is usually too large to be fit into memory in practice. However, compared to the offline algorithms, the existing streaming algorithms for submodular maximization generally have weaker capabilities in that they handle more limited problem constraints or achieve weaker performance bounds, due to the more stringent requirements under the streaming setting. Another classification of the existing algorithms is that they concentrate on either monotone or non-monotone submodular functions. As monotone submodular function is a special case of non-monotone submodular function, we will concentrate on non-monotone submodular maximization in this paper.


  • Open Access

    Practical Parallel Algorithms for Submodular Maximization Subject to a Knapsack Constraint with Nearly Optimal Adaptivity

    by Shuang Cui, Kai Han, Jing Tang, He Huang, Xueying Li, Aakas Zhiyuli

    Submodular maximization has wide applications in machine learning and data mining, where massive datasets have brought the great need for designing efficient and parallelizable algorithms. One measure of the parallelizability of a submodular maximization algorithm is its adaptivity complexity, which indicates the number of sequential rounds where a polynomial number of queries to the objective function can be executed in parallel. In this paper, we study the problem of non-monotone submodular maximization subject to a knapsack constraint, and propose the first combinatorial algorithm achieving an (8+epsilon)-approximation under O(log n) adaptive complexity, which is optimal up to a factor of O(loglog n). Moreover, under slightly larger adaptivity, we also propose approximation algorithms with nearly optimal query complexity of O(n), while achieving better approximation ratios. We show that our algorithms can also be applied to the special case of submodular maximization subject to a cardinality constraint, and achieve performance bounds comparable with those of state-of-the-art algorithms. Finally, the effectiveness of our approach is demonstrated by extensive experiments on real-world applications.


  • Open Access

    Streaming Algorithms for Constrained Submodular Maximization

    by Shuang Cui, Kai Han, Jing Tang, He Huang, Xueying Li, Zhiyu Li

    Due to the pervasive "diminishing returns" property appeared in data-intensive applications, submodular maximization problems have aroused great attention from both the machine learning community and the computation theory community. During the last decades, a lot of algorithms have been proposed for submodular maximization subject to various constraints [4, 6, 8], and these algorithms can be used in numerous applications including sensor placement [9], clustering [5], network design [13], and so on. The existing algorithms for submodular maximization can be roughly classified into offline algorithms and streaming algorithms; the former assume full access to the whole dataset at any time (e.g.,[4, 10]), while the latter only require an amount of space which is nearly linear in the maximum size of a feasible solution (e.g., [1, 7]). Apparently, streaming algorithms are more useful in big data applications, as the whole data set is usually too large to be fit into memory in practice. However, compared to the offline algorithms, the existing streaming algorithms for submodular maximization generally have weaker capabilities in that they handle more limited problem constraints or achieve weaker performance bounds, due to the more stringent requirements under the streaming setting. Another classification of the existing algorithms is that they concentrate on either monotone or non-monotone submodular functions. As monotone submodular function is a special case of non-monotone submodular function, we will concentrate on non-monotone submodular maximization in this paper.