Author name cluster

Hongyan Li

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.

13 papers

1 author row

AAMAS Conference 2026 Conference Paper

From Knowledge to Causality: Self-Supervised Representation Learning for Granger Causal Discovery in Groups of Time Series

Bo Liu
Hongyan Li
Shenda Hong

Causal inference among groups of time series is crucial for understanding complex systems like brain networks and climate dynamics. Existing methods often rely on simple aggregation to represent groups, leading to significant information loss and suboptimal causal discovery. We propose CausalKGR, a novel framework that learns expressive latent representations for Granger causal discovery. By introducing a Knowledge-Conditional Attention mechanism, CausalKGR distills temporal knowledge into a compact latent space, capturing both intra-group dynamics and inter-group interactions. Extensive experiments on synthetic and real-world datasets demonstrate that CausalKGR significantly outperforms state-of-the-art baselines in accuracy and interpretability.

PDF

JBHI Journal 2025 Journal Article

Development of a tongue image-based machine learning tool for the diagnosis of colorectal cancer: a prospective multicentre clinical cohort study

Xiaohe Sun
Letian Huang
Libo Qu
Cheng Chen
Xing Zeng
Zuojian Zhou
Hongyan Li
Jin Sun

Colorectal cancer (CRC) remains a persistent major global health burden, with traditional diagnostic methods like colonoscopy suffering from suboptimal patient compliance rates. This study develops an intelligent diagnostic model based on tongue images to assist in CRC diagnosis, leveraging the integrative potential of traditional tongue diagnosis and modern machine learning. Between June 2023 and July 2024, we collected and processed 1, 389 tongue images from CRC patients and 1, 543 from non-colorectal cancer (NCRC) participants. Our methodology combines innovative image segmentation using the Segment Anything Model (SAM) with Grounding DINO, extracts both hand-crafted features (color, texture, shape) and deep learning features via Swin-Transformer, and employs feature fusion and selection techniques. The diagnostic model achieves an accuracy of 87. 93% (F1-score: 0. 9072) in internal validation. In an independent external cohort of 119 CRC patients and 221 NCRC participants, it demonstrates 85. 18% precision (recall: 85%, F1-score: 0. 8507). This noninvasive, cost-effective approach demonstrates significant potential as a complementary screening tool for CRC, particularly in regions with limited access to conventional diagnostic resources.

Details DOI

YNIMG Journal 2025 Journal Article

Screening tools for subjective cognitive decline and mild cognitive impairment based on task-state prefrontal functional connectivity: a functional near-infrared spectroscopy study

Zhengping Pu
Hongna Huang
Man Li
Hongyan Li
Xiaoyan Shen
Lizhao Du
Qingfeng Wu
Xiaomei Fang

BACKGROUND: Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) carry the risk of progression to dementia, and accurate screening methods for these conditions are urgently needed. Studies have suggested the potential ability of functional near-infrared spectroscopy (fNIRS) to identify MCI and SCD. The present fNIRS study aimed to develop an early screening method for SCD and MCI based on activated prefrontal functional connectivity (FC) during the performance of cognitive scales and subject-wise cross-validation via machine learning. METHODS: Activated prefrontal FC data measured by fNIRS were collected from 55 normal controls, 80 SCD patients, and 111 MCI patients. Differences in FC were analyzed among the groups, and FC strength and cognitive scale performance were extracted as features to build classification and predictive models through machine learning. Model performance was assessed based on accuracy, specificity, sensitivity, and area under the curve (AUC) with 95 % confidence interval (CI) values. RESULTS: Statistical analysis revealed a trend toward more impaired prefrontal FC with declining cognitive function. Prediction models were built by combining features of prefrontal FC and cognitive scale performance and applying machine learning models, The models showed generally satisfactory abilities to differentiate among the three groups, especially those employing linear discriminant analysis, logistic regression, and support vector machine. Accuracies of 92.0 % for MCI vs. NC, 80.0 % for MCI vs. SCD, and 76.1 % for SCD vs. NC were achieved, and the highest AUC values were 97.0 % (95 % CI: 94.6 %-99.3 %) for MCI vs. NC, 87.0 % (95 % CI: 81.5 %-92.5 %) for MCI vs. SCD, and 79.2 % (95 % CI: 71.0 %-87.3 %) for SCD vs. NC. CONCLUSION: The developed screening method based on fNIRS and machine learning has the potential to predict early-stage cognitive impairment based on prefrontal FC data collected during cognitive scale-induced activation.

Details DOI

IJCAI Conference 2025 Conference Paper

T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models

Yunfeng Ge
Jiawei Li
Yiji Zhao
Haomin Wen
Zhao Li
Meikang Qiu
Hongyan Li
Ming Jin

Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series data across domains. While diffusion models have achieved remarkable success in Text-to-X (e. g. , vision and audio data) generation, their use in time series generation remains limit. Existing approaches face two critical limitations: (1) reliance on domain-specific captions that generalize poorly, and (2) inability to generate time series of arbitrary length, limiting real-world use. In this work, we first introduce a new multimodal dataset containing over 600, 000 high-resolution text-time series pairs. Second, we propose Text-to-Series (T2S), a diffusion-based framework that bridges the gap between natural language and time series in a domain-agnostic manner. It employs a length-adaptive VAE to encode time series of varying lengths into consistent latent embeddings. On top of that, T2S effectively aligns textual representations with latent embeddings by utilizing Flow Matching and employing DiT as the denoiser. We train T2S in an interleaved paradigm across multiple lengths, allowing it to generate sequences of arbitrary lengths. Extensive evaluations demonstrate that T2S achieves state-of-the-art performance across 13 datasets spanning 12 domains.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Retrieval-Augmented Diffusion Models for Time Series Forecasting

Jingwei Liu
Ling Yang
Hongyan Li
Shenda Hong

While time series diffusion models have received considerable focus from many recent works, the performance of existing models remains highly unstable. Factors limiting time series diffusion models include insufficient time series datasets and the absence of guidance. To address these limitations, we propose a Retrieval-Augmented Time series Diffusion model (RATD). The framework of RATD consists of two parts: an embedding-based retrieval process and a reference-guided diffusion model. In the first part, RATD retrieves the time series that are most relevant to historical time series from the database as references. The references are utilized to guide the denoising process in the second part. Our approach allows leveraging meaningful samples within the database to aid in sampling, thus maximizing the utilization of datasets. Meanwhile, this reference-guided mechanism also compensates for the deficiencies of existing time series diffusion models in terms of guidance. Experiments and visualizations on multiple datasets demonstrate the effectiveness of our approach, particularly in complicated prediction tasks. Our code is available at https: //github. com/stanliu96/RATD

PDF Details DOI

IJCAI Conference 2022 Conference Paper

Hypergraph Structure Learning for Hypergraph Neural Networks

Derun Cai
Moxian Song
Chenxi Sun
Baofeng Zhang
Shenda Hong
Hongyan Li

Hypergraphs are natural and expressive modeling tools to encode high-order relationships among entities. Several variations of Hypergraph Neural Networks (HGNNs) are proposed to learn the node representations and complex relationships in the hypergraphs. Most current approaches assume that the input hypergraph structure accurately depicts the relations in the hypergraphs. However, the input hypergraph structure inevitably contains noise, task-irrelevant information, or false-negative connections. Treating the input hypergraph structure as ground-truth information unavoidably leads to sub-optimal performance. In this paper, we propose a Hypergraph Structure Learning (HSL) framework, which optimizes the hypergraph structure and the HGNNs simultaneously in an end-to-end way. HSL learns an informative and concise hypergraph structure that is optimized for downstream tasks. To efficiently learn the hypergraph structure, HSL adopts a two-stage sampling process: hyperedge sampling for pruning redundant hyperedges and incident node sampling for pruning irrelevant incident nodes and discovering potential implicit connections. The consistency between the optimized structure and the original structure is maintained by the intra-hyperedge contrastive learning module. The sampling processes are jointly optimized with HGNNs towards the objective of the downstream tasks. Experiments conducted on 7 datasets show shat HSL outperforms the state-of-the-art baselines while adaptively sparsifying hypergraph structures.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data

Chenxi Sun
Shenda Hong
Moxian Song
Yen-Hsiu Chou
Yongyue Sun
Derun Cai
Hongyan Li

Prediction based on Irregularly Sampled Time Series (ISTS) is of wide concern in real-world applications. For more accurate prediction, methods had better grasp more data characteristics. Different from ordinary time series, ISTS is characterized by irregular time intervals of intra-series and different sampling rates of inter-series. However, existing methods have suboptimal predictions due to artificially introducing new dependencies in a time series and biasedly learning relations among time series when modeling these two characteristics. In this work, we propose a novel Time Encoding (TE) mechanism. TE can embed the time information as time vectors in the complex domain. It has the properties of absolute distance and relative distance under different sampling rates, which helps to represent two irregularities. Meanwhile, we create a new model named Time Encoding Echo State Network (TE-ESN). It is the first ESNs-based model that can process ISTS data. Besides, TE-ESN incorporates long short-term memories and series fusion to grasp horizontal and vertical relations. Experiments on one chaos system and three real-world datasets show that TE-ESN performs better than all baselines and has better reservoir property.

PDF Details DOI

AAAI Conference 2019 Conference Paper

GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination

Junyuan Shang
Cao Xiao
Tengfei Ma
Hongyan Li
Jimeng Sun

Recent progress in deep learning is revolutionizing the healthcare domain including providing solutions to medication recommendations, especially recommending medication combination for patients with complex health conditions. Existing approaches either do not customize based on patient health history, or ignore existing knowledge on drug-drug interactions (DDI) that might lead to adverse outcomes. To fill this gap, we propose the Graph Augmented Memory Networks (GAMENet), which integrates the drug-drug interactions knowledge graph by a memory module implemented as a graph convolutional networks, and models longitudinal patient records as the query. It is trained end-to-end to provide safe and personalized recommendation of medication combination. We demonstrate the effectiveness and safety of GAMENet by comparing with several state-of-the-art methods on real EHR data. GAMENet outperformed all baselines in all effectiveness measures, and also achieved 3. 60% DDI rate reduction from existing EHR data.

PDF Details

IJCAI Conference 2019 Conference Paper

K-margin-based Residual-Convolution-Recurrent Neural Network for Atrial Fibrillation Detection

Yuxi Zhou
Shenda Hong
Junyuan Shang
Meng Wu
Qingyun Wang
Hongyan Li
Junqing Xie

Atrial Fibrillation (AF) is an abnormal heart rhythm which can trigger cardiac arrest and sudden death. Nevertheless, its interpretation is mostly done by medical experts due to high error rates of computerized interpretation. One study found that only about 66% of AF were correctly recognized from noisy ECGs. This is in part due to insufficient training data, class skewness, as well as semantical ambiguities caused by noisy segments in an ECG record. In this paper, we propose a K-margin-based Residual-Convolution-Recurrent neural network (K-margin-based RCR-net) for AF detection from noisy ECGs. In detail, a skewness-driven dynamic augmentation method is employed to handle the problems of data inadequacy and class imbalance. A novel RCR-net is proposed to automatically extract both long-term rhythm-level and local heartbeat-level characters. Finally, we present a K-margin-based diagnosis model to automatically focus on the most important parts of an ECG record and handle noise by naturally exploiting expected consistency among the segments associated for each record. The experimental results demonstrate that the proposed method with 0. 8125 F1NAOP score outperforms all state-of-the-art deep learning methods for AF detection task by 6. 8%.

PDF Details

IJCAI Conference 2019 Conference Paper

MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

Shenda Hong
Cao Xiao
Tengfei Ma
Hongyan Li
Jimeng Sun

Electrocardiography (ECG) signals are commonly used to diagnose various cardiac abnormalities. Recently, deep learning models showed initial success on modeling ECG data, however they are mostly black-box, thus lack interpretability needed for clinical usage. In this work, we propose MultIlevel kNowledge-guided Attention networks (MINA) that predict heart diseases from ECG signals with intuitive explanation aligned with medical knowledge. By extracting multilevel (beat-, rhythm- and frequency-level) domain knowledge features separately, MINA combines the medical knowledge and ECG data via a multilevel attention model, making the learned models highly interpretable. Our experiments showed MINA achieved PR-AUC 0. 9436 (outperforming the best baseline by 5. 51%) in real world ECG dataset. Finally, MINA also demonstrated robust performance and strong interpretability against signal distortion and noise contamination.

PDF Details

IJCAI Conference 2019 Conference Paper

RDPD: Rich Data Helps Poor Data via Imitation

Shenda Hong
Cao Xiao
Trong Nghia Hoang
Tengfei Ma
Hongyan Li
Jimeng Sun

In many situations, we need to build and deploy separate models in related environments with different data qualities. For example, an environment with strong observation equipments (e. g. , intensive care units) often provides high-quality multi-modal data, which are acquired from multiple sensory devices and have rich-feature representations. On the other hand, an environment with poor observation equipment (e. g. , at home) only provides low-quality, uni-modal data with poor-feature representations. To deploy a competitive model in a poor-data environment without requiring direct access to multi-modal data acquired from a rich-data environment, this paper develops and presents a knowledge distillation (KD) method (RDPD) to enhance a predictive model trained on poor data using knowledge distilled from a high-complexity model trained on rich, private data. We evaluated RDPD on three real-world datasets and shown that its distilled model consistently outperformed all baselines across all datasets, especially achieving the greatest performance improvement over a model trained only on low-quality data by 24. 56% on PR-AUC and 12. 21% on ROC-AUC, and over that of a state-of-the-art KD model by 5. 91% on PR-AUC and 4. 44% on ROC-AUC.

PDF Details

AAAI Conference 2018 Short Paper

Generative Adversarial Network for Abstractive Text Summarization

Linqing Liu
Yao Lu
Min Yang
Qiang Qu
Jia Zhu
Hongyan Li

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization. We also build a discriminator which attempts to distinguish the generated summary from the ground truth summary. Extensive experiments demonstrate that our model achieves competitive ROUGE scores with the state-of-the-art methods on CNN/Daily Mail dataset. Qualitatively, we show that our model is able to generate more abstractive, readable and diverse summaries1.

PDF Details

AAAI Conference 2018 Short Paper

Negative-Aware Influence Maximization on Social Networks

Yipeng Chen
Hongyan Li
Qiang Qu

How to minimize the impact of negative users within the maximal set of inﬂuenced users? The Inﬂuenced Maximization (IM) is important for various applications. However, few studies consider the negative impact of some of the inﬂuenced users. We propose a negative-aware inﬂuence maximization problem by considering users’ negative impact. A novel algorithm is proposed to solve the problem. Experiments on real-world datasets show the proposed algorithm can achieve 70% improvement on average in expected inﬂuence compared with rivals.

PDF Details