Hanzhu Chen
PhD Student at 
University of Science and Technology of China (USTC)
Previously Computer Science and Technology BS Student at Southwest University
About
Hanzhu Chen’s SAC-KG employs LLMs as automated constructors for domain-specific knowledge graphs. Chen is a PhD student at the University of Science and Technology of China within the MIRA Lab and a research intern at Huawei Noah’s Ark Lab. Their research focuses on the intersection of LLMs and KGs, notably developing Coarse-to-fine highlighting to reduce hallucinations and Knowledge graph finetuning to improve knowledge manipulation. Prior to joining Huawei, they completed a year-long internship at Alibaba DAMO Academy. Chen’s broader work in ML and graph learning includes Ropo for robust preference optimization and Neural krylov iteration for accelerating linear solvers. They earned a BS from Southwest University in 2021.
Experience
PhD Student
2021 – Present
University of Science and Technology of China (USTC)
Advised by Prof. Jie Wang in the MIRA Lab.
2021 – Present
Intern
Oct 2024 – Present
Noah’s Ark Lab, Huawei Technologies
Oct 2024 – Present
Intern
Jul 2023 – Jul 2024
Alibaba DAMO Academy
Jul 2023 – Jul 2024
Computer Science and Technology BS Student
2017 – 2021
Southwest University
2017 – 2021
Papers15
Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM) -- which enhances models with up-to-date knowledge -- emerges as a promising method to reduce hallucination. However, existing RALMs may instead exacerbate hallucination when retrieving lengthy contexts. To address this challenge, we propose COFT, a novel COarse-to-Fine highlighTing method to focus on different granularity-level key texts, thereby avoiding getting lost in lengthy contexts. Specifically, COFT consists of three components: recaller, scorer, and selector. First, recaller applies a knowledge graph to extract potential key entities in a given context. Second, scorer measures the importance of each entity by calculating its contextual weight. Finally, selector selects high contextual weight entities with a dynamic threshold algorithm and highlights the corresponding paragraphs, sentences, or words in a coarse-to-fine manner. Extensive experiments on the knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over in the F1 score metric. Moreover, COFT also exhibits remarkable versatility across various long-form tasks, such as reading comprehension and question answering.
Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important downstream tasks. To encode the attributes and graph structures simultaneously, recent studies integrate pre-trained models with graph neural networks (GNNs), where pre-trained models serve as node encoders (NEs) to encode the attributes. As jointly training large NEs and GNNs on large-scale graphs suffers from severe scalability issues, many methods propose to train NEs and GNNs separately. Consequently, they do not take feature convolutions in GNNs into consideration in the training phase of NEs, leading to a significant learning bias relative to the joint training. To address this challenge, we propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias. More importantly, we show that LD converges to the optimal objective function values by the joint training under mild assumptions. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.
Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
Inductive relation prediction (IRP) -- where entities can be different during training and inference -- has shown great power for completing evolving knowledge graphs. Existing works mainly focus on using graph neural networks (GNNs) to learn the representation of the subgraph induced from the target link, which can be seen as an implicit rule-mining process to measure the plausibility of the target link. However, these methods cannot differentiate the target link and other links during message passing, hence the final subgraph representation will contain irrelevant rule information to the target link, which reduces the reasoning performance and severely hinders the applications for real-world scenarios. To tackle this problem, we propose a novel single-source edge-wise GNN model to learn the Rule-inducEd Subgraph represenTations (REST), which encodes relevant rules and eliminates irrelevant rules within the subgraph. Specifically, we propose a single-source initialization approach to initialize edge features only for the target link, which guarantees the relevance of mined rules and target link. Then we propose several RNN-based functions for edge-wise message passing to model the sequential property of mined rules. REST is a simple and effective approach with theoretical support to learn the rule-induced subgraph representation. Moreover, REST does not need node labeling, which significantly accelerates the subgraph preprocessing time by up to \textbf{11.66}. Experiments on inductive relation prediction benchmarks demonstrate the effectiveness of our REST. Our code is available at this https URL
Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity-independent manner. Many popular methods mainly focus on modeling graph-level features, while the edge-level interactions -- especially the semantic correlations between relations -- have been less explored. However, we notice a desirable property of semantic correlations between relations is that they are inherently edge-level and entity-independent. This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task. Inspired by this observation, we propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations that are highly correlated to their topological structures within subgraphs. Specifically, we prove that semantic correlations between any two relations can be categorized into seven topological patterns, and then proposes Relational Correlation Network (RCN) to learn the importance of each pattern. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph that can effectively preserve complete topological patterns within the subgraph. Extensive experiments demonstrate that TACO effectively unifies the graph-level information and edge-level interactions to jointly perform reasoning, leading to a superior performance over existing state-of-the-art methods for the inductive link prediction task.
