Author name cluster

Jian Yuan

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

2 author rows

NeurIPS Conference 2025 Conference Paper

LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models

Qianyue Hao
Yiwen Song
Qingmin Liao
Jian Yuan
Yong Li

Policy exploration is critical in reinforcement learning (RL), where existing approaches include $\epsilon$-greedy, Gaussian process, etc. However, these approaches utilize preset stochastic processes and are indiscriminately applied in all kinds of RL tasks without considering task-specific features that influence policy exploration. Moreover, during RL training, the evolution of such stochastic processes is rigid, which typically only incorporates a decay in the variance, failing to adjust flexibly according to the agent's real-time learning status. Inspired by the analyzing and reasoning capability of large language models (LLMs), we design **LLM-Explorer** to adaptively generate task-specific exploration strategies with LLMs, enhancing the policy exploration in RL. In our design, we sample the learning trajectory of the agent during the RL training in a given task and prompt the LLM to analyze the agent's current policy learning status and then generate a probability distribution for future policy exploration. Updating the probability distribution periodically, we derive a stochastic process specialized for the particular task and dynamically adjusted to adapt to the learning process. Our design is a plug-in module compatible with various widely applied RL algorithms, including the DQN series, DDPG, TD3, and any possible variants developed based on them. Through extensive experiments on the Atari and MuJoCo benchmarks, we demonstrate LLM-Explorer's capability to enhance RL policy exploration, achieving an average performance improvement up to 37. 27%. Our code is open-source at https: //github. com/tsinghua-fib-lab/LLM-Explorer for reproducibility.

PDF Details

IJCAI Conference 2025 Conference Paper

OpenCarbon: A Contrastive Learning-based Cross-Modality Neural Approach for High-Resolution Carbon Emission Prediction Using Open Data

Jinwei Zeng
Yu Liu
Guozhen Zhang
Jingtao Ding
Yuming Lin
Jian Yuan
Yong Li

Accurately estimating high-resolution carbon emissions is crucial for effective emission governance and mitigation planning. While conventional methods for precise carbon accounting are hindered by substantial data collection efforts, the rise of open data and advanced learning techniques offers a promising solution. Once an open data-based prediction model is developed and trained, it can easily infer emissions for new areas based on available open data. To address this, we incorporate two modalities of open data, satellite images and point-of-interest (POI) data, to predict high-resolution urban carbon emissions, with satellite images providing macroscopic and static and POI data offering fine-grained and relatively dynamic functionality information. However, estimating high-resolution carbon emissions presents two significant challenges: the intertwined and implicit effects of various functionalities on carbon emissions, and the complex spatial contiguity correlations that give rise to the agglomeration effect. Our model, OpenCarbon, features two major designs that target the challenges: a cross-modality information extraction and fusion module to extract complementary functionality information from two modules and model their interactions, and a neighborhood-informed aggregation module to capture the spatial contiguity correlations. Extensive experiments demonstrate our model's superiority, with a significant performance gain of 26. 6% on R2. Further generalizability tests and case studies also show OpenCarbon's capacity to capture the intrinsic relation between urban functionalities and carbon emissions, validating its potential to empower efficient carbon governance and targeted carbon mitigation planning. Codes and data are available: https: //github. com/JinweiZzz/OpenCarbon.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

TreeKV: Smooth Key-Value Cache Compression with Tree Structures

Ziwei He
Jian Yuan
Haoli Bai
Jingwen Leng
Bo Jiang

Efficient key-value (KV) cache compression is critical for scaling transformer-based Large Language Models (LLMs) in long sequences and resource-limited settings. Existing methods evict tokens based on their positions or importance, but position-based strategies can miss crucial information outside predefined regions, while those relying on global importance scores resulting in strong regional biases, limiting the KV cache's overall context retention and potentially impairing the performance of LLMs on complex tasks. Our wavelet analysis reveals that as tokens approach the end of sequence, their contributions to generation gradually increase and tends to diverge more from neighboring tokens, indicating a smooth transition with increasing complexity and variability from distant to nearby context. Motivated by this observation, we propose TreeKV, an intuitive, training-free method that employs a tree structure for smooth cache compression. TreeKV maintains a fixed cache size, allowing LLMs to deliver high-quality output in long text scenarios and is applicable during both the generation and prefilling stages. TreeKV consistently surpasses all baseline models in language modeling tasks on PG19 and OpenWebText2, allowing LLMs trained with short context window to generalize to longer window with a 16x cache reduction. On the Longbench benchmark, TreeKV achieves the best performance with only 6% of the budget at optimal efficiency.

PDF Details DOI

TIST Journal 2024 Journal Article

Empowering Predictive Modeling by GAN-based Causal Information Learning

Jinwei Zeng
Guozhen Zhang
Jian Yuan
Yong Li
Depeng Jin

Generally speaking, we can easily specify many causal relationships in the prediction tasks of ubiquitous computing, such as human activity prediction, mobility prediction, and health prediction. However, most of the existing methods in these fields failed to take advantage of this prior causal knowledge. They typically make predictions only based on correlations in the data, which hinders the prediction performance in real-world scenarios, because a distribution shift between training data and testing data generally exists. To fill in this gap, we proposed a Generative Adversarial Network (GAN)-based Causal Information Learning prediction framework, which can effectively leverage causal information to improve the prediction performance of existing ubiquitous computing deep learning models. Specifically, faced with a unique challenge that the treatment variable, referring to the intervention that influences the target in a causal relationship, is generally continuous in ubiquitous computing, the framework employs a representation learning approach with a GAN-based deep learning model. By projecting all variables except the treatment into a latent space, it effectively minimizes confounding bias and leverages the learned latent representation for accurate predictions. In this way, it deals with the continuous treatment challenge, and in the meantime, it can be easily integrated with existing deep learning models to lift their prediction performance in practical scenarios with causal information. Extensive experiments on two large-scale real-world datasets demonstrate its superior performance over multiple state-of-the-art baselines. We also propose an analytical framework together with extensive experiments to empirically show that our framework achieves better performance gain under two conditions: when the distribution differences between the training data and the testing data are more significant and when the treatment effects are larger. Overall, this work suggests that learning causal information is a promising way to improve the prediction performance of ubiquitous computing tasks. We open both our dataset and code 1 and call for more research attention in this area.

Details DOI

AAAI Conference 2024 Conference Paper

Estimating On-Road Transportation Carbon Emissions from Open Data of Road Network and Origin-Destination Flow Data

Jinwei Zeng
Yu Liu
Jingtao Ding
Jian Yuan
Yong Li

Accounting for over 20% of the total carbon emissions, the precise estimation of on-road transportation carbon emissions is crucial for carbon emission monitoring and efficient mitigation policy formulation. However, existing estimation methods typically depend on hard-to-collect individual statistics of vehicle miles traveled to calculate emissions, thereby suffering from high data collection difficulty. To relieve this issue by utilizing the strong pattern recognition of artificial intelligence, we incorporate two sources of open data representative of the transportation demand and capacity factors, the origin-destination (OD) flow data and the road network data, to build a hierarchical heterogeneous graph learning method for on-road carbon emission estimation (HENCE). Specifically, a hierarchical graph consisting of the road network level, community level, and region level is constructed to model the multi-scale road network-based connectivity and travel connection between spatial areas. Heterogeneous graphs consisting of OD links and spatial links are further built at both the community level and region level to capture the intrinsic interactions between travel demand and road network accessibility. Extensive experiments on two large-scale real-world datasets demonstrate HENCE's effectiveness and superiority with R-squared exceeding 0.75 and outperforming baselines by 9.60% on average, validating its success in pioneering the use of artificial intelligence to empower carbon emission management and sustainability development. The implementation codes are available at this link: https://github.com/tsinghua-fib-lab/HENCE.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction

Qianyue Hao
Jingyang Fan
Fengli Xu
Jian Yuan
Yong Li

Citation networks are critical infrastructures of modern science, serving as intricate webs of past literature and enabling researchers to navigate the knowledge production system. To mine information hiding in the link space of such networks, predicting which previous papers (candidates) will a new paper (query) cite is a critical problem that has long been studied. However, an important gap remains unaddressed: the roles of a paper's citations vary significantly, ranging from foundational knowledge basis to superficial contexts. Distinguishing these roles requires a deeper understanding of the logical relationships among papers, beyond simple edges in citation networks. The emergence of large language models (LLMs) with textual reasoning capabilities offers new possibilities for discerning these relationships, but there are two major challenges. First, in practice, a new paper may select its citations from gigantic existing papers, where the combined texts far exceed the context length of LLMs. Second, logical relationships between papers are often implicit, and directly prompting an LLM to predict citations may lead to results based primarily on surface-level textual similarities, rather than the deeper logical reasoning required. In this paper, we introduce the novel concept of core citation, which identifies the critical references that go beyond superficial mentions. Thereby, we elevate the citation prediction task from a simple binary classification to a more nuanced problem: distinguishing core citations from both superficial citations and non-citations. To address this, we propose $\textbf{HLM-Cite}$, a $\textbf{H}$ybrid $\textbf{L}$anguage $\textbf{M}$odel workflow for citation prediction, which combines embedding and generative LMs. We design a curriculum finetune procedure to adapt a pretrained text embedding model to coarsely retrieve high-likelihood core citations from vast candidate sets and then design an LLM agentic workflow to rank the retrieved papers through one-shot reasoning, revealing the implicit relationships among papers. With the two-stage pipeline, we can scale the candidate sets to 100K papers, vastly exceeding the size handled by existing methods. We evaluate HLM-Cite on a dataset across 19 scientific fields, demonstrating a 17. 6\% performance improvement comparing SOTA methods. Our code is open-source at https: //github. com/tsinghua-fib-lab/H-LM for reproducibility.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models

Jingyuan Zhu
Shiyu Li
Yuxuan Liu
Jian Yuan
Ping Huang
Jiulong Shan
Huimin Ma

Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing multi-class objects and dense objects with occlusions remain limited. This paper presents ODGEN, a novel method to generate high-quality images conditioned on bounding boxes, thereby facilitating data synthesis for object detection. Given a domain-specific object detection dataset, we first fine-tune a pre-trained diffusion model on both cropped foreground objects and entire images to fit target distributions. Then we propose to control the diffusion model using synthesized visual prompts with spatial constraints and object-wise textual descriptions. ODGEN exhibits robustness in handling complex scenes and specific domains. Further, we design a dataset synthesis pipeline to evaluate ODGEN on 7 domain-specific benchmarks to demonstrate its effectiveness. Adding training data generated by ODGEN improves up to 25. 3% mAP@. 50: .95 with object detectors like YOLOv5 and YOLOv7, outperforming prior controllable generative methods. In addition, we design an evaluation protocol based on COCO-2014 to validate ODGEN in general domains and observe an advantage up to 5. 6% in mAP@. 50: .95 against existing methods.

PDF Details DOI

TIST Journal 2024 Journal Article

RCCNet: A Spatial-Temporal Neural Network Model for Logistics Delivery Timely Rate Prediction

Jinhui Yi
Huan Yan
Haotian Wang
Jian Yuan
Yong Li

In logistics service, the delivery timely rate is a key experience indicator, which is highly essential to the competitive advantage of express companies. Prediction on it enables intervention on couriers with low predicted results in advance, thus ensuring employee productivity and customer satisfaction. Currently, few related works focus on couriers’ level delivery timely rate prediction, and there are complex spatial correlations between couriers and road districts in the express scenario, which makes traditional real-time prediction approaches hard to utilize. To deal with this, we propose a deep spatial-temporal neural network, RCCNet to model spatial-temporal correlations. Specifically, we adopt Node2vec, which can encode the road network-based graph directly to capture spatial correlations between road districts. Further, we calculate couriers’ historical time-series similarity to build a graph and employ graph convolutional networks to capture the correlation between couriers. We also leverage historical sequential information with long short-term memory networks. We conduct experiments with real-world express datasets. Compared with other competitive baseline methods widely used in industry, the experiment results demonstrate its superior performance over multiple baselines.

Details DOI

TIST Journal 2023 Journal Article

DAS: Efficient Street View Image Sampling for Urban Prediction

Guozhen Zhang
Jinhui Yi
Jian Yuan
Yong Li
Depeng Jin

Street view data is one of the most common data sources for urban prediction tasks, such as estimating socioeconomic status, sensing physical urban changes, and identifying urban villages. Typical research in this field consists of two steps: acquiring a dataset with a street view image sampling algorithm and designing a prediction algorithm for urban prediction tasks. However, most of the previous research focuses on the prediction algorithms, leaving the sampling algorithms underexplored. To fill this gap, we set out to investigate how different street view image sampling algorithms affect the performance of the follow-up tasks and develop an effective street view image sampling algorithm for urban prediction. Through a comprehensive analysis of the performance of different sampling algorithms in three of the most common urban prediction tasks, including commercial activeness prediction, urban liveliness prediction, and urban population prediction, we provide solid empirical evidence that the sampling algorithm significantly affects the performance of the prediction model. Specifically, the performance differences of different sampling algorithms can reach over 25%. Further, we revealed that the sampling step size and the sampling quality are two important factors that affect the performance of a sampling algorithm, while the sampling angle has little influence. Inspired by our analysis results, we propose an effective street view image sampling algorithm, DAS, which contains a denoising module and an adaptive sampling module. It can dynamically adjust the sampling step size to adapt to the optimal size for each region and get rid of the impact of noise images in the meantime. Experiments on three large-scale datasets demonstrate its superior performance over multiple state-of-the-art baselines, and further ablation study shows the effectiveness of each module. Finally, through a thorough discussion of our findings and experimental results, we provide insights into the street view image sampling algorithm design, and we call for more researches in this blank area.

Details DOI

IJCAI Conference 2023 Conference Paper

Prediction with Incomplete Data under Agnostic Mask Distribution Shift

Yichen Zhu
Jian Yuan
Bo Jiang
Tao Lin
Haiming Jin
Xinbing Wang
Chenghu Zhou

Data with missing values is ubiquitous in many applications. Recent years have witnessed increasing attention on prediction with only incomplete data consisting of observed features and a mask that indicates the missing pattern. Existing methods assume that the training and testing distributions are the same, which may be violated in real-world scenarios. In this paper, we consider prediction with incomplete data in the presence of distribution shift. We focus on the case where the underlying joint distribution of complete features and label is invariant, but the missing pattern, i. e. , mask distribution may shift agnostically between training and testing. To achieve generalization, we leverage the observation that for each mask, there is an invariant optimal predictor. To avoid the exponential explosion when learning them separately, we approximate the optimal predictors jointly using a double parameterization technique. This has the undesirable side effect of allowing the learned predictors to rely on the intra-mask correlation and that between features and mask. We perform decorrelation to minimize this effect. Combining the techniques above, we propose a novel prediction method called StableMiss. Extensive experiments on both synthetic and real-world datasets show that StableMiss is robust and outperforms state-of-the-art methods under agnostic mask distribution shift.

PDF Details DOI

AAMAS Conference 2022 Conference Paper

Learning to Advise and Learning from Advice in Cooperative Multiagent Reinforcement Learning

Yue Jin
Shuangqing Wei
Jian Yuan
Xudong Zhang

We propose a novel policy-level generative adversarial learning framework to enhance cooperative multiagent reinforcement learning (MARL), which consists of a centralized advisor, MARL agents and discriminators. The advisor is realized through a dual graph convolutional network (DualGCN) to give advice to agents from a global perspective via fusing decision information, resolving spatial conflicts, and maintaining temporal continuity. Each discriminator trained can distinguish between the policies of the advisor and an agent. Leveraging the discriminator’s judgment, each agent learns to match with the advised policy in addition to learning by its own exploration, which accelerates learning and enhances policy performance. Additionally, an advisor boosting method which incorporates the relevant suggestion made by the discriminators into the training of DualGCN is proposed to further help improve MARL agents. We validate our methods in cooperative navigation tasks. Results demonstrate that our method outperforms baseline methods in terms of both learning efficiency and policy efficacy.

PDF

ICML Conference 2022 Conference Paper

Supervised Off-Policy Ranking

Yue Jin
Yue Zhang
Tao Qin 0001
Xudong Zhang 0001
Jian Yuan
Houqiang Li
Tie-Yan Liu

Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end goal of OPE is to compare two or multiple candidate policies and choose a good one, which is a much simpler task than precisely evaluating their true performance; and (2) there are usually multiple policies that have been deployed to serve users in real-world systems and thus the true performance of these policies can be known. Inspired by the two observations, in this work, we study a new problem, supervised off-policy ranking (SOPR), which aims to rank a set of target policies based on supervised learning by leveraging off-policy data and policies with known performance. We propose a method to solve SOPR, which learns a policy scoring model by minimizing a ranking loss of the training policies rather than estimating the precise policy performance. The scoring model in our method, a hierarchical Transformer based model, maps a set of state-action pairs to a score, where the state of each pair comes from the off-policy data and the action is taken by a target policy on the state in an offline manner. Extensive experiments on public datasets show that our method outperforms baseline methods in terms of rank correlation, regret value, and stability. Our code is publicly available at GitHub.

Details

AIIM Journal 2020 Journal Article

Classification of myocardial infarction based on hybrid feature extraction and artificial intelligence tools by adopting tunable-Q wavelet transform (TQWT), variational mode decomposition (VMD) and neural networks

Wei Zeng
Jian Yuan
Chengzhi Yuan
Qinghui Wang
Fenglin Liu
Ying Wang

Cardiovascular diseases (CVD) is the leading cause of human mortality and morbidity around the world, in which myocardial infarction (MI) is a silent condition that irreversibly damages the heart muscles. Currently, electrocardiogram (ECG) is widely used by the clinicians to diagnose MI patients due to its inexpensiveness and non-invasive nature. Pathological alterations provoked by MI cause slow conduction by increasing axial resistance on coupling between cells. This issue may cause abnormal patterns in the dynamics of the tip of the cardiac vector in the ECG signals. However, manual interpretation of the pathological alternations induced by MI is a time-consuming, tedious and subjective task. To overcome such disadvantages, computer-aided diagnosis techniques including signal processing and artificial intelligence tools have been developed. In this study we propose a novel technique for automatic detection of MI based on hybrid feature extraction and artificial intelligence tools. Tunable quality factor ( Q -factor) wavelet transform (TQWT), variational mode decomposition (VMD) and phase space reconstruction (PSR) are utilized to extract representative features to form cardiac vectors with synthesis of the standard 12-lead and Frank XYZ leads. They are combined with neural networks to model, identify and detect abnormal patterns in the dynamics of cardiac system caused by MI. First, 12-lead ECG signals are reduced to 3-dimensional VCG signals, which are synthesized with Frank XYZ leads to build a hybrid 4-dimensional cardiac vector. Second, this vector is decomposed into a set of frequency subbands with a number of decomposition levels by using the TQWT method. Third, VMD is employed to decompose the subband of the 4-dimensional cardiac vector into different intrinsic modes, in which the first intrinsic mode contains the majority of the cardiac vector's energy and is considered to be the predominant intrinsic mode. It is selected to construct the reference variable for analysis. Fourth, phase space of the reference variable is reconstructed, in which the properties associated with the nonlinear cardiac system dynamics are preserved. Three-dimensional (3D) PSR together with Euclidean distance (ED) has been utilized to derive features, which demonstrate significant difference in cardiac system dynamics between normal (healthy) and MI cardiac vector signals. Fifth, cardiac system dynamics can be modeled and identified using neural networks, which employ the ED of 3D PSR of the reference variable as the input features. The difference of cardiac system dynamics between healthy control and MI cardiac vector is computed and used for the detection of MI based on a bank of estimators. Finally, data sets, which include conventional 12-lead and Frank XYZ leads ECG signal fragments from 148 patients with MI and 52 healthy controls from PTB diagnostic ECG database, are used for evaluation. By using the 10-fold cross-validation style, the achieved average classification accuracy is reported to be 97. 98%. Currently, ST segment evaluation is one of the major and traditional ways for the MI detection. However, there exist weak or even undetectable ST segments in many ECG signals. Since the proposed method does not rely on the information of ST waves, it can serve as a complementary MI detection algorithm in the intensive care unit (ICU) of hospitals to assist the clinicians in confirming their diagnosis. Overall, our results verify that the proposed features may satisfactorily reflect cardiac system dynamics, and are complementary to the existing ECG features for automatic cardiac function analysis.

Details DOI