XZXingrui Zhuo

Xingrui Zhuo

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xingrui Zhuo has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Generation-Then-Discrimination: Hierarchical Entity-Relation Decoder for Relational Triplet Extraction

    by Xiaonan Jing, Gongqing Wu, Xingrui Zhuo

    Relational Triplet Extraction (RTE) is the key to organizing a clear knowledge graph from unstructured text. Benefiting from the representational power of pre-trained language models (PLMs), RTE methods have achieved impressive performance. Existing PLM-based approaches can be broadly categorized into two frameworks: generative and discriminative. Generative models leverage PLMs to capture the complete semantics of entities and directly generate relational triplets. While discriminative models predict entity positions under relation-specific constraints, ensuring relational uniqueness. However, both paradigms suffer from inherent limitations: generative models are susceptible to hallucination when generating relations. In contrast, discriminative models are sensitive to the prediction errors of entity positions. In this work, we demonstrate that the respective weaknesses of the two frameworks can be effectively mitigated by leveraging the strengths that complement one another. Consequently, we propose a Hierarchical entity-relation Decoder for Relational Triplet Extraction (HD-RTE), which synergistically integrates the advantages of generative and discriminative modeling within a two-stage hierarchical framework. In the first stage, to alleviate the error in entity position prediction, a generative PLM is employed to extract semantically complete entities by leveraging its implicit knowledge and global context understanding ability. In the second stage, to avoid hallucination in relation generation, a discriminative relation decoder operates on the extracted entity pairs. By modeling fine-grained contextual interactions through the attention mechanism, the decoder can precisely determine the relations between entities. Experimental results on widely adopted benchmark datasets, including NYT and WebNLG, demonstrate that HD-RTE delivers state-of-the-art performance, particularly in scenarios involving complex entity-relation networks.

  • Open Access

    Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction

    by Xiaonan Jing, Gongqing Wu, Xingrui Zhuo, Lang Sun, Jiapu Wang

    Open-domain Relational Triplet Extraction (ORTE) is the foundation for mining structured knowledge without predefined schemas. Despite the impressive in-context learning capabilities of Large Language Models (LLMs), existing methods are hindered by their reliance on static, heuristic-driven prompting strategies. Due to the lack of reflection mechanisms required to internalize erroneous signals, these methods exhibit vulnerability in semantic ambiguity, often making erroneous extraction patterns permanent. To address this bottleneck, we propose a Knowledge Reconstruction-driven Prompt Optimization (KRPO) framework to assist LLMs in continuously improving their extraction capabilities for complex ORTE task flows. Specifically, we design a self-evaluation mechanism based on knowledge restoration, which provides intrinsic feedback signals by projecting structured triplets into semantic consistency scores. Subsequently, we propose a prompt optimizer based on a textual gradient that can internalize historical experiences to iteratively optimize prompts, which can better guide LLMs to handle subsequent extraction tasks. Furthermore, to alleviate relation redundancy, we design a relation canonicalization memory that collects representative relations and provides semantically distinct schemas for the triplets. Extensive experiments across three datasets show that KRPO significantly outperforms strong baselines in the extraction F1 score.


  • Open Access

    Progressive Prefix-Memory Tuning for Complex Logical Query Answering on Knowledge Graphs

    by Xingrui Zhuo, Shirui Pan, Jiapu Wang, Gongqing Wu, Zan Zhang, Rui Li, Zizhong Wei, Xindong Wu

    Conducting complex logical queries over knowledge graphs remains a significant challenge. Recent research has successfully leveraged Pre-trained Language Models (PLMs) to tackle Knowledge Graph Complex Query Answering (KGCQA) tasks, which is attributed to PLMs' ability to comprehend logical semantics of queries through context learning. However, existing PLM-based KGCQA methods usually overlook the harm of disordered syntax or fragmented contexts within a serialized query, posing the problem of “impossible language” to limit PLMs in grasping the logical semantics. To address this problem, we propose a Progressive Prefix-Memory Tuning (PPMT) framework for KGCQA tasks, which effectively rectifies erroneous segments in serialized queries to assist PLMs in query answering. First, we propose a prefix-memory rectification mechanism embedded in a PLM module. This mechanism assigns rectification parameters in memory stores to polish the language segments of entities, relations, and queries through specific prefixes. To further capture the logical semantics in queries, we design a progressive fine-tuning strategy, which optimizes our model through a conditional gradient update process guided by knowledge translation constraints. Extensive experiments on widely used KGCQA benchmarks demonstrate the significant superiority of PPMT in terms of HR@3 and MRR. Our codes are available at https://github.com/lazyloafer/PPMT.


  • Open Access

    Multi-Hop Multi-View Memory Transformer for Session-Based Recommendation

    by Xingrui Zhuo, Shengsheng Qian, Jun Hu, Fuxin Dai, Kangyi Lin, Gongqing Wu

    A Session-Based Recommendation (SBR) seeks to predict users’ future item preferences by analyzing their interactions with previously clicked items. In recent approaches, Graph Neural Networks (GNNs) have been commonly applied to capture item relations within a session to infer user intentions. However, these GNN-based methods typically struggle with feature ambiguity between the sequential session information and the item conversion within an item graph, which may impede the model’s ability to accurately infer user intentions. In this article, we propose a novel Multi-hop Multi-view Memory Transformer (M 3 T) to effectively integrate the sequence-view information and relation conversion (graph-view information) of items in a session. First, we propose a Multi-view Memory Transformer (M 2 T) module to concurrently obtain multi-view information of items. Then, a set of trainable memory matrices are employed to store sharable item features, which mitigates cross-view item feature ambiguity. To comprehensively capture latent user intentions, an M 3 T framework is designed to integrate user intentions across different hops of an item graph. Specifically, a k-order power method is proposed to manage the item graph to alleviate the over-smoothing problem when obtaining high-order relations of items. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our method.


  • Open Access

    A Lightweight, Effective, and Efficient Model for Label Aggregation in Crowdsourcing

    by Yi Yang, Zhong-Qiu Zhao, Gongqing Wu, Xingrui Zhuo, Qing Liu, Quan Bai, Weihua Li

    Due to the presence of noise in crowdsourced labels, label aggregation (LA) has become a standard procedure for post-processing these labels. LA methods estimate true labels from crowdsourced labels by modeling worker quality. However, most existing LA methods are iterative in nature. They require multiple passes through all crowdsourced labels, jointly and iteratively updating true labels and worker qualities until a termination condition is met. As a result, these methods are burdened with high space and time complexities, which restrict their applicability in scenarios where scalability and online aggregation are essential. Furthermore, defining a suitable termination condition for iterative algorithms can be challenging. In this article, we view LA as a dynamic system and represent it as a Dynamic Bayesian Network. From this dynamic model, we derive two lightweight and scalable algorithms: LAonepassand LAtwopass. These algorithms can efficiently and effectively estimate worker qualities and true labels by traversing all labels at most twice, thereby eliminating the need for explicit termination conditions and multiple traversals over the crowdsourced labels. Due to their dynamic nature, the proposed algorithms are also capable of performing label aggregation online. We provide theoretical proof of the convergence property of the proposed algorithms and bound the error of the estimated worker qualities. Furthermore, we analyze the space and time complexities of our proposed algorithms, demonstrating their equivalence to those of majority voting. Through experiments conducted on 20 real-world datasets, we demonstrate that our proposed algorithms can effectively and efficiently aggregate labels in both offline and online settings, even though they traverse all labels at most twice. The code is onhttps://github.com/yyang318/LA_onepass.


  • Geometric-Contextual Mutual Infomax Path Aggregation for Relation Reasoning on Knowledge Graph

    by Xingrui Zhuo, Gongqing Wu, Zan Zhang, Xindong Wu

    Relation reasoning in K nowledge G raph C ompletion (KGC) aims at predicting missing relations between entities. Recently, effective KGC methods have usually focused on exploring the path pattern between entities, such as reward-based path walking and path context mining, to complete target relations. However, these methods typically suffer from two challenges: 1) They have difficulty in handling the individual representation limitation of candidate paths when there are no paths that directly represent latent relations between entities; 2) They overlook the biases of path context induction, which leads to unreasonable information interfering with the model's reasoning. To manage these challenges, a G eometric- C ontextual M utual I nfomax (GCMI) path aggregator is proposed for relation reasoning. First, we design an attentive path aggregator with a shared Transformer encoder to capture the contexts from several candidate paths parallelly and integrate these contexts to sufficiently represent the latent relations of each entity pair for reasoning. Then, the GCMI modules are proposed to constrain the local and global biases of path context induction in the Transformer encoder and the path aggregator, respectively, by a straightforward geometric rule. Extensive experiments on 32 real-world relation reasoning tasks demonstrate that our method significantly outperforms 8 state-of-the-art baselines in terms of AP and AUC.


  • Label Enhanced Graph Attention Network for Truth Inference

    by Ningjing Zhao, Xingrui Zhuo, Gongqing Wu, Zan Zhang


  • Open Access

    Crowdsourcing Truth Inference via Reliability-Driven Multi-View Graph Embedding

    by Gongqing Wu, Xingrui Zhuo, Xianyu Bao, Xuegang Hu, Richang Hong, Xindong Wu

    Crowdsourcing truth inference aims to assign a correct answer to each task from candidate answers that are provided by crowdsourced workers. A common approach is to generate workers’ reliabilities to represent the quality of answers. Although crowdsourced triples can be converted into various crowdsourced relationships, the available related methods are not effective in capturing these relationships to alleviate the harm to inference that is caused by conflicting answers. In this research, we propose aReliability-drivenMulti-viewGraphEmbedding framework forTruthinference (TiReMGE), which explores multiple crowdsourced relationships by organically integrating worker reliabilities into a graph space that is constructed from crowdsourced triples. Specifically, to create an interactive environment, we propose a reliability-driven initialization criterion for initializing vectors of tasks and workers as interactive carriers of reliabilities. From the perspective of multiple crowdsourced relationships, a multi-view graph embedding framework is proposed for reliability information interaction on a task-worker graph, which encodes latent crowdsourced relationships into vectors of workers and tasks for reliability update and truth inference. A heritable reliability updating method based on the Lagrange multiplier method is proposed to obtain reliabilities that match the quality of workers for interaction by a novel constraint law. Our ultimate goal is to minimize the Euclidean distance between the encoded task vector and the answer that is provided by a worker with high reliability. Extensive experimental results on nine real-world datasets demonstrate that TiReMGE significantly outperforms the nine state-of-the-art baselines.


  • Semantic Fusion Enhanced Event Detection via Multi-Graph Attention Network with Skip Connection

    by Gongqing Wu, Zhenya Lu, Xingrui Zhuo, Xianyu Bao, Xindong Wu

    The target of event detection (ED) is to recognize and categorize event triggers in a given text. Because dependency trees transmit extensive structural information that has been proven effective, most contemporary ED approaches rely primarily on syntactic information. The majority of these methods, however, are ineffective due to two issues: a) how to mine and use both first-order and multi-order syntactic relations, and b) loss of information due to external dependency analysis toolbox. In this paper, we overcome the aforementioned two challenges by proposing the Semantic Fusion Enhanced Event Detection via Multi-Graph Attention Network with Skip Connection (SMGED) model. To solve the first problem mentioned above, SMGED constructs a multi-layer graph attention network with skip connections to capture syntactic relations with different orders and avoid information over-propagation. Then to solve the second problem, an information fusion module is proposed to fuse the contextual information and syntactic relations of each word to compensate for the lost information. We carried out extensive experiments and compared the proposed SMGED to existing methods. The comparison results validated the proposed model's effectiveness and superiority.