HSHui Sun

Hui Sun

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hui Sun has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Tree species identity is associated with rhizosphere microbiome assembly via root metabolite‐mediated feedbacks in subtropical forests

    by Yuemei Zhang, Junchen Ye, Yao Kang, Yangchunzi Liao, Ziwen Jiao, Wenjing Meng, Lin Chang, Bing Liu, Yilin Li, Ziwen Gao, et al.

    The rhizosphere microbiome is critical for forest ecological functions, yet the mechanisms through which tree species identity and neighbour tree interactions are associated with its assembly remain poorly understood. Using Illumina MiSeq and liquid chromatography–mass spectrometry (LC–MS), we investigated how tree species (pine vs. liquidambar) and forest composition (pure vs. mixed) shape rhizosphere microbial communities and root metabolites in subtropical forests. Rhizosphere fungal community structure differed significantly across rhizosphere types, whereas bacterial community and metabolite profiles differed primarily between the pure pine forest and other forest types. Predicted functional shifts included a decline in cellulolytic bacteria (−27%) and an increase in denitrifying groups (+54%), with ectomycorrhizal fungi enriched in mixed than pure forests ( p < 0.05). Metabolite profiling revealed that lipids, organic acids and sugars were the most abundant compound classes, with 55 metabolites differentially abundant between pure pine and mixed forest rhizospheres. Rhizosphere metabolite profiles were significantly correlated with microbial community structure ( p < 0.05). Specific microbe–metabolite associations were identified; fatty acids positively correlated with oligotrophic bacteria (WPS‐2), sugars with denitrifiers ( Reyranella ) and dipeptides with the beneficial fungus Penicillium . These results demonstrate that tree species identity is associated with rhizosphere microbiome assembly via root metabolite‐associated feedbacks, which correlate with soil nutrient cycling. This provides a mechanistic, function‐oriented framework for understanding plant–microbiome interaction and harnessing them to enhance ecosystem resilience. Read the free Plain Language Summary for this article on the Journal blog.

  • Mitigating Negative Transfer via Reducing Environmental Disagreement

    by Hui Sun, Zheng Xie, Hao-Yuan He, Ming Li

    Unsupervised Domain Adaptation (UDA) focuses on transferring knowledge from a labeled source domain to an unlabeled target domain, addressing the challenge of domain shift. Significant domain shifts hinder effective knowledge transfer, leading to negative transfer and deteriorating model performance. Therefore, mitigating negative transfer is essential. This study revisits negative transfer through the lens of causally disentangled learning, emphasizing cross-domain discriminative disagreement on non-causal environmental features as a critical factor. Our theoretical analysis reveals that overreliance on non-causal environmental features as the environment evolves can cause discriminative disagreements (termed environmental disagreement), thereby resulting in negative transfer. To address this, we propose Reducing Environmental Disagreement (RED), which disentangles each sample into domain-invariant causal features and domain-specific non-causal environmental features via adversarially training domain-specific environmental feature extractors in the opposite domains. Subsequently, RED estimates and reduces environmental disagreement based on domain-specific non-causal environmental features. Experimental results confirm that RED effectively mitigates negative transfer and achieves state-of-the-art performance.


  • Post-Incorporating Code Structural Knowledge Into Pretrained Models via ICL for Code Translation

    by Yali Du, Hui Sun, Ming Li

    Code translation migrates codebases across programming languages. Recently, large language models (LLMs) have achieved significant advancements in software mining. However, handling the syntactic structure of source code remains a challenge. Classic syntax-aware methods depend on intricate model architectures and loss functions, rendering their integration into LLM training resource-intensive. This paper employs in-context learning (ICL), which directly integrates task exemplars into the input context, to post-incorporate code structural knowledge into pre-trained LLMs. We revisit exemplar selection in ICL from an information-theoretic perspective, proposing that list-wise selection based on information coverage is more precise and general objective than traditional methods based on combine similarity and diversity. To address the challenges of quantifying information coverage, we introduce a surrogate measure, Coverage of Abstract Syntax Tree (CAST), measuring maximum subtree coverage between ASTs of test source code and exemplars. Furthermore, we formulate the NP-hard CAST maximization for exemplar selection and prove that it is a standard submodular maximization problem. Therefore, we propose a greedy algorithm for CAST submodular maximization, which theoretically guarantees a (1 − 1/e)-approximate solution in polynomial time complexity. Our method is the first training-free and model-agnostic approach to post-incorporate code structural knowledge into existing LLMs at test time. Experimental results show that our method significantly improves LLMs performance in code translation and reveals two meaningful insights: 1) Code structural knowledge can be effectively post-incorporated into pre-trained LLMs during inference, despite being overlooked during training; 2) Scaling up model size or training data does not lead to the emergence of code structural knowledge, underscoring the necessity of explicitly considering code syntactic structure.


  • Open Access

    Learning Personalizable Clustered Embedding for Recommender Systems

    by Yizhou Chen, Guangda Huzhang, Anxiang Zeng, Qingtao Yu, Hui Sun, Heng-Yi Li, Jingyi Li, Yabo Ni, Han Yu, Zhiming Zhou

    In recent years, recommender systems have advanced rapidly, where embedding learning for users and items plays a critical role. A standard method learns a unique embedding vector for each user and item. However, such a method has two important limitations in real-world applications: (1) it is hard to learn embeddings that generalize well for users and items that have rare interactions, and (2) it may incur unbearably high memory costs when the number of users and items scales up. Existing approaches either can only address one of the limitations or have flawed overall performances. In this article, we propose Clustered Embedding Learning (CEL) as an integrated solution to these two problems. CEL is a plug-and-play embedding learning framework that can be combined with any differentiable feature interaction model. It is capable of achieving improved performance, especially for cold users and items, with reduced memory cost. CEL enables automatic and dynamic clustering of users and items in a top-down fashion, where clustered entities could jointly learn a shared embedding. The accelerated version of CEL has an optimal time complexity, which supports efficient online updates. Theoretically, we prove the identifiability and the existence of a unique optimal number of clusters for CEL in the context of nonnegative matrix factorization. Empirically, we validate the effectiveness of CEL on three public datasets and one business dataset, showing its consistently superior performance against state-of-the-art methods. In particular, when incorporating CEL into the business model, it brings an improvement of \(+0.6\%\) in AUC, which translates into a significant revenue gain; meanwhile, the size of the embedding table gets 2,650 times smaller. Additionally, we demonstrate that if there is enough memory, learning a personalized embedding for each user and item around their clustering centers is feasible and can further boost performance. In this article, we enhance and extend the personalization technique we initially proposed in our earlier work [ 4 ], which introduced an offset regularization to prevent personalized embeddings from drifting too far away from the central (cluster) embedding, thereby mitigating overfitting. However, in [ 4 ], we simply applied a uniform regularization weight across all embeddings, which, given the considerable variation in the number of their associated interactions, is suboptimal. To address this, we investigate in this article the strategies for non-uniform offset regularization that adjusts regularization weights according to the number of associated interactions, which leads to significant improvements compared with uniform offset regularization. Furthermore, we extend CEL into Meta-CEL, factoring in future personalization during cluster optimization, which leads to additional enhancements in personalization performance.

  • Open Access

    A Joint Learning Model with Variational Interaction for Multilingual Program Translation

    by Yali Du, Hui Sun, Ming Li

    Programs implemented in various programming languages form the foundation of software applications. To alleviate the burden of program migration and facilitate the development of software systems, automated program translation across languages has garnered significant attention. Previous approaches primarily focus on pairwise translation paradigms, learning translation between pairs of languages using bilingual parallel data. However, parallel data is difficult to collect for some language pairs, and the distribution of program semantics across languages can shift, posing challenges for pairwise program translation. In this paper, we argue that jointly learning a unified model to translate code across multiple programming languages is superior to separately learning from bilingual parallel data. We propose Variational Interaction for Multilingual Program Translation (VIM-PT), a disentanglement-based generative approach that jointly trains a unified model for multilingual program translation across multiple languages. VIM-PT disentangles code into language-shared and language-specific features, using variational inference and interaction information with a novel lower bound, then achieves program translation through conditional generation. VIM-PT demonstrates four advantages: 1) captures language-shared information more accurately from various implementations and improves the quality of multilingual program translation, 2) mines and leverages the capability of non-parallel data, 3) addresses the distribution shift of program semantics across languages, 4) and serves as a unified model, reducing deployment complexity.


  • Open Access

    Clustered Embedding Learning for Recommender Systems

    by Yizhou Chen, Guangda Huzhang, Anxiang Zeng, Qingtao Yu, Hui Sun, Heng-Yi Li, Jingyi Li, Yabo Ni, Han Yu, Zhiming Zhou

    In recent years, recommender systems have advanced rapidly, where embedding learning for users and items plays a critical role. A standard method learns a unique embedding vector for each user and item. However, such a method has two important limitations in real-world applications: 1) it is hard to learn embeddings that generalize well for users and items with rare interactions; and 2) it may incur unbearably high memory costs when the number of users and items scales up. Existing approaches either can only address one of the limitations or have flawed overall performances. In this paper, we propose Clustered Embedding Learning (CEL) as an integrated solution to these two problems. CEL is a plug-and-play embedding learning framework that can be combined with any differentiable feature interaction model. It is capable of achieving improved performance, especially for cold users and items, with reduced memory cost. CEL enables automatic and dynamic clustering of users and items in a top-down fashion, where clustered entities jointly learn a shared embedding. The accelerated version of CEL has an optimal time complexity, which supports efficient online updates. Theoretically, we prove the identifiability and the existence of a unique optimal number of clusters for CEL in the context of nonnegative matrix factorization. Empirically, we validate the effectiveness of CEL on three public datasets and one business dataset, showing its consistently superior performance against current state-of-the-art methods. In particular, when incorporating CEL into the business model, it brings an improvement of in AUC, which translates into a significant revenue gain; meanwhile, the size of the embedding table gets 2650 times smaller.1


  • Open Access

    News Recommendation System Based on Topic Embedding and Knowledge Embedding

    by Haojie Zhang, Hui Sun, Baiwen Qi, Zhidong Shen

    News recommendation system is designed to deal with massive news and provide personalized recommendations for users. Accurately capturing user preferences and modeling news and users is the key to news recommendation. In this paper, we propose a new framework, news recommendation system based on topic embedding and knowledge embedding (NRTK). NRTK handle news titles that users have clicked on from two perspectives to obtain news and user representation embedding :1) extracting explicit and latent topic features from news and mining users' preferences for them in historical behaviors; 2) extracting entities and propagating users' potential preferences in the knowledge graph. Experiments in a real-world dataset validate the effectiveness and efficiency of our approach.