Author name cluster

Yi Zheng

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.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

Discovering Decoupled Functional Modules in Large Language Models

Yanke Yu
Jin Li
Ying Sun
Ping Li
Zhefeng Wang
Yi Zheng

Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions into modules remains highly unexplored. To bridge this gap, we formulate a function module discovery problem and propose an Unsupervised LLM Cross-layer MOdule Discovery (ULCMOD) framework that simultaneously disentangles the large set of neurons in the entire LLM into modules while discovering the topics of input samples related to these modules. Our framework introduces a novel objective function and an efficient Iterative Decoupling (IterD) algorithm. Extensive experiments show that our method discovers high-quality, disentangled modules that capture more meaningful semantic information and achieve superior performance in various downstream tasks. Moreover, our qualitative analysis reveals that the discovered modules show function comprehensiveness, function hierarchy, and clear function spatial arrangement within LLMs. Our work provides a novel tool for interpreting LLMs' function modules, filling a critical gap in LLMs' interpretability research.

PDF Details DOI

JBHI Journal 2026 Journal Article

Leads-Adaptive Fetal Electrocardiogram Extraction Using Attention-Based BiLSTM

Ying Zhu
Le Xu
Shenao Chen
Limin Diao
Yi Zheng
Varun G Menon

Extracting the fetal electrocardiogram (fECG) from the abdominal electrocardiogram (AECG) will help clinicians accurately discern fetal cardiac rhythm patterns. Nevertheless, the intricacies inherent in the clinical setting often precipitate signal anomalies within AECG recordings, thereby rendering traditional extraction methodologies suboptimal. This work proposes a deep learning-based fECG extraction method designed for the adaptive extraction of fECG signals from multi-lead AECG inputs. The proposed methodology is predicated upon a bidirectional long short-term memory (BiLSTM) architecture, augmented with a deep supervision subnetwork and an attention mechanism module. The attention module quantifies the inter-channel relevance of the input AECG through the computation of attention weights, facilitating subsequent feature fusion along the channel axis. This process effectively mitigates the impact of defective channels on the output. Comprehensive evaluations were conducted on publicly available datasets, encompassing scenarios with channel loss and benchmarked against established models. The results demonstrate the proposed model's efficacy in extracting fECG signals under diverse channel defect conditions. Ablation studies further validate the critical role of the attention module in enhancing the model's resilience to channel anomalies. Additionally, the reliability of the extracted fECG signals was corroborated through experiments involving input signal masking. The method proposed in this work is helpful for the clinical deployment of the fECG extraction in fetal cardiac rhythm assessment.

Details DOI

YNIMG Journal 2024 Journal Article

The heritability and structural correlates of resting-state fMRI complexity

Yi Zhen
Yaqian Yang
Yi Zheng
Xin Wang
Longzhao Liu
Zhiming Zheng
Hongwei Zheng
Shaoting Tang

The complexity of fMRI signals quantifies temporal dynamics of spontaneous neural activity, which has been increasingly recognized as providing important insights into cognitive functions and psychiatric disorders. However, its heritability and structural underpinnings are not well understood. Here, we utilize multi-scale sample entropy to extract resting-state fMRI complexity in a large healthy adult sample from the Human Connectome Project. We show that fMRI complexity at multiple time scales is heritable in broad brain regions. Heritability estimates are modest and regionally variable. We relate fMRI complexity to brain structure including surface area, cortical myelination, cortical thickness, subcortical volumes, and total brain volume. We find that surface area is negatively correlated with fine-scale complexity and positively correlated with coarse-scale complexity in most cortical regions, especially the association cortex. Most of these correlations are related to common genetic and environmental effects. We also find positive correlations between cortical myelination and fMRI complexity at fine scales and negative correlations at coarse scales in the prefrontal cortex, lateral temporal lobe, precuneus, lateral parietal cortex, and cingulate cortex, with these correlations mainly attributed to common environmental effects. We detect few significant associations between fMRI complexity and cortical thickness. Despite the non-significant association with total brain volume, fMRI complexity exhibits significant correlations with subcortical volumes in the hippocampus, cerebellum, putamen, and pallidum at certain scales. Collectively, our work establishes the genetic basis and structural correlates of resting-state fMRI complexity across multiple scales, supporting its potential application as an endophenotype for psychiatric disorders.

Details DOI

EAAI Journal 2022 Journal Article

Knowledge-based operation optimization of a distillation unit integrating feedstock property considerations

Sihong Li
Yi Zheng
Shaoyuan Li
Meng Huang

The distillation unit (DU) is an essential product separation unit in refineries. The process operation of DU is directly related to the quality and yield of the final petroleum products. The DU studied in this work is deeply troubled by the varying feedstock properties, which aggravates the difficulty of process operation. To determine the proper operation variables, a knowledge-based operation optimization (KOO) strategy of a DU is proposed in this paper. The KOO strategy is composed of a supervision module and an optimization module. First, the operating conditions are divided into four types based on the feedstock properties. In supervision module, an improved bar-shaped convolutional neural network supervision model (IBS-CNN-based SM) is developed to monitor the operating conditions. The model output which represents the current operating condition information is transmitted to the lower optimization module. In optimization module, the fuzzy-logic-based optimization strategy is designed to adjust two temperature variables — the top temperature of the distillation column (TTDC) and the outlet temperature of the re-boiling furnace (OTRF) to ensure the product quality requirements. Industrial experiments have illustrated the KOO strategy could adapt to the varying feedstock properties. During the experiment, the proposed KOO strategy improved the product qualification rate from 86. 67% to 93. 34% and saved the consumption of gas and cooling water to a certain extent.

Details DOI

ICML Conference 2017 Conference Paper

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis

Rong Ge 0001
Chi Jin 0001
Yi Zheng

In this paper we develop a new framework that captures the common landscape underlying the common non-convex low-rank matrix problems including matrix sensing, matrix completion and robust PCA. In particular, we show for all above problems (including asymmetric cases): 1) all local minima are also globally optimal; 2) no high-order saddle points exists. These results explain why simple algorithms such as stochastic gradient descent have global converge, and efficiently optimize these non-convex objective functions in practice. Our framework connects and simplifies the existing analyses on optimization landscapes for matrix sensing and symmetric matrix completion. The framework naturally leads to new results for asymmetric matrix completion and robust PCA.

Details

AAAI Conference 2016 Conference Paper

Reading the Videos: Temporal Labeling for Crowdsourced Time-Sync Videos Based on Semantic Embedding

Guangyi Lv
Tong Xu
Enhong Chen
Qi Liu
Yi Zheng

Recent years have witnessed the boom of online sharing media contents, which raise signiﬁcant challenges in effective management and retrieval. Though a large amount of efforts have been made, precise retrieval on video shots with certain topics has been largely ignored. At the same time, due to the popularity of novel time-sync comments, or so-called “bullet-screen comments”, video semantics could be now combined with timestamps to support further research on temporal video labeling. In this paper, we propose a novel video understanding framework to assign temporal labels on highlighted video shots. To be speciﬁc, due to the informal expression of bullet-screen comments, we ﬁrst propose a temporal deep structured semantic model (T-DSSM) to represent comments into semantic vectors by taking advantage of their temporal correlation. Then, video highlights are recognized and labeled via semantic vectors in a supervised way. Extensive experiments on a real-world dataset prove that our framework could effectively label video highlights with a signiﬁcant margin compared with baselines, which clearly validates the potential of our framework on video understanding, as well as bullet-screen comments interpretation.

PDF Details

IJCAI Conference 2016 Conference Paper

Weakly-Supervised Deep Learning for Customer Review Sentiment Classification

Ziyu Guan
Long Chen
Wei Zhao
Yi Zheng
Shulong Tan
Deng Cai

Sentiment analysis is one of the key challenges for mining online user generated content. In this work, we focus on customer reviews which are an important form of opinionated content. The goal is to identify each sentence's semantic orientation (e. g. positive or negative) of a review. Traditional sentiment classification methods often involve substantial human efforts, e. g. lexicon construction, feature engineering. In recent years, deep learning has emerged as an effective means for solving sentiment classification problems. A neural network intrinsically learns a useful representation automatically without human efforts. However, the success of deep learning highly relies on the availability of large-scale training data. In this paper, we propose a novel deep learning framework for review sentiment classification which employs prevalently available ratings as weak supervision signals. The framework consists of two steps: (1) learn a high level representation (embedding space) which captures the general sentiment distribution of sentences through rating information; (2) add a classification layer on top of the embedding layer and use labeled sentences for supervised fine-tuning. Experiments on review data obtained from Amazon show the efficacy of our method and its superiority over baseline methods.

PDF Details

IJCAI Conference 2013 Conference Paper

PageRank with Priors: An Influence Propagation Perspective

Biao Xiang
Qi Liu
Enhong Chen
Hui Xiong
Yi Zheng
Yu Yang

Recent years have witnessed increased interests in measuring authority and modelling inﬂuence in social networks. For a long time, PageRank has been widely used for authority computation and has also been adopted as a solid baseline for evaluating social inﬂuence related applications. However, the connection between authority measurement and in- ﬂuence modelling is not clearly established. To this end, in this paper, we provide a focused study on understanding of PageRank as well as the relationship between PageRank and social inﬂuence analysis. Along this line, we ﬁrst propose a linear social inﬂuence model and reveal that this model is essentially PageRank with prior. Also, we show that the authority computation by PageRank can be enhanced with more generalized priors. Moreover, to deal with the computational challenge of PageRank with general priors, we provide an upper bound for top authoritative nodes identiﬁcation. Finally, the experimental results on the scientiﬁc collaboration network validate the effectiveness of the proposed social inﬂuence model.

PDF Details DOI