Author name cluster

Ge Yu

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.

11 papers

2 author rows

AAAI Conference 2025 Conference Paper

Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological Oscillations

Heng Rao
Yu Gu
Jason Zipeng Zhang
Ge Yu
Yang Cao
Minghan Chen

Biological oscillations are periodic changes in various signaling processes crucial for the proper functioning of living organisms. These oscillations are modeled by ordinary differential equations, with coefficient variations leading to diverse periodic behaviors, typically measured by oscillatory frequencies. This paper explores sampling techniques for neural networks to model the relationship between system coefficients and oscillatory frequency. However, the scarcity of oscillations in the vast coefficient space results in many samples exhibiting non-periodic behaviors, and small coefficient changes near oscillation boundaries can significantly alter oscillatory properties. This leads to non-oscillatory bias and boundary sensitivity, making accurate predictions difficult. While existing importance and uncertainty sampling approaches partially mitigate these challenges, they either fail to resolve the sensitivity problem or result in redundant sampling. To address these limitations, we propose the Hierarchical Gradient-based Genetic Sampling (HGGS) framework, which improves the accuracy of neural network predictions for biological oscillations. The first layer, Gradient-based Filtering, extracts sensitive oscillation boundaries and removes redundant non-oscillatory samples, creating a balanced coarse dataset. The second layer, Multi-grid Genetic Sampling, utilizes residual information to refine these boundaries and explore new high-residual regions, increasing data diversity for model training. Experimental results demonstrate that HGGS outperforms seven comparative sampling methods across four biological systems, highlighting its effectiveness in enhancing sampling and prediction accuracy.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

LBMKGC: Large Model-Driven Balanced Multimodal Knowledge Graph Completion

Yuan Guo
Qian Ma
Hui Li
Qiao Ning
Furui Zhan
Yu Gu
Ge Yu
Shikai Guo

Multi-modal Knowledge Graph Completion (MMKGC) aims to predict missing entities, relations, or attributes in knowledge graphs by collaboratively modeling the triple structure and multimodal information (e. g. , text, images, videos) associated with entities. This approach facilitates the automatic discovery of previously unobserved factual knowledge. However, existing MMKGC methods encounter several critical challenges: (i) the imbalance of inter-entity information across different modalities; (ii) the heterogeneity of intra-entity multimodal information; and (iii) for a given entity, the informational contributions of different modalities are inconsistent across contexts. In this paper, we propose a novel L arge model-driven B alanced M ultimodal K nowledge G raph C ompletion framework, termed LBMKGC. Subsequently, to bridge the semantic gap between heterogeneous modalities, LBMKGC aligns the multimodal embeddings of entities semantically by using the CLIP (Contrastive Language-Image Pre-Training) model. Furthermore, LBMKGC adaptively fuses multimodal embeddings with relational guidance by distinguishing between the perceptual and conceptual attributes of triples. Finally, extensive experiments conducted against 21 state-of-the-art baselines demonstrate that LBMKGC achieves superior performance across diverse datasets and scenarios while maintaining efficiency and generalizability. Our code and data are publicly available at: https: //github. com/guoynow/LBMKGC.

PDF Details

NeurIPS Conference 2025 Conference Paper

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

Pengcheng Huang
Zhenghao Liu
Yukun Yan
Haiyan Zhao
Xiaoyuan Yi
Hao Chen
Zhiyuan Liu
Maosong Sun

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence. However, they remain susceptible to unfaithful generation, where outputs contradict retrieved context despite its relevance and accuracy. Existing approaches aiming to improve faithfulness primarily focus on enhancing the utilization of external context, but often overlook the persistent influence of internal parametric knowledge during generation. In this work, we investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases. Building on this insight, we propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs and calibrating the model toward retrieved knowledge. To evaluate our approach, we introduce CoFaithfulQA, a benchmark specifically designed to evaluate faithfulness in scenarios where internal knowledge conflicts with accurate external evidence. Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory. These findings underscore the importance of mitigating internal knowledge dominance and provide a new direction for improving LLM trustworthiness in RAG. All codes are available at https: //github. com/OpenBMB/ParamMute.

PDF Details

IJCAI Conference 2025 Conference Paper

Priority Guided Explanation for Knowledge Tracing with Dual Ranking and Similarity Consistency

Fan Li
Tiancheng Zhang
Yifang Yin
Minghe Yu
Mengxiang Wang
Ge Yu

Knowledge tracing plays a pivotal role in enabling personalized learning on online platforms. While deep learning-based approaches have achieved impressive predictive performance, their limited interpretability poses a significant barrier to practical adoption. Existing explanation methods primarily focus on specific model architectures and fall short in 1) explicitly prioritizing critical interactions to generate fine-grained explanations, and 2) maintaining similarity consistency across interaction importance. These limitations hinder actionable insights for improving student outcomes. To bridge the gap, we propose a model-agnostic approach that provides enhanced explanations applicable to diverse knowledge tracing methods. Specifically, we propose a novel ranking loss designed to explicitly optimize the importance ranking of past interactions by comparing their corresponding perturbed outputs. Furthermore, we introduce a similarity loss to capture temporal dependencies, ensuring consistency in the assigned importance scores for conceptually similar interactions. Extensive experiments conducted on various knowledge tracing models and benchmark datasets demonstrate substantial enhancements in explanation quality.

PDF Details DOI

ICRA Conference 2023 Conference Paper

Congestion Prediction for Large Fleets of Mobile Robots

Ge Yu
Michael T. Wolf

This paper introduces a deep learning (DL) approach to predicting congestion delays in large multi-robot systems. The problem is motivated by real-world problems in modern logistics automation, such as a warehouse with hundreds to thousands of coordinated mobile robots. Here, the large scale, the complexity of the control software, and the uncertainties of the robots' dynamics make direct (simulated) prediction of future robot states impractical. We propose predicting delays associated with future spatiotemporal locations, and we show this is useful for improving system performance via incorporating the predictions into path planning and travel time estimation. Our DL model uses convolutional long short-term memory (ConvLSTM) as the core structure, takes the historical congestion condition and planned paths as input, and generates the delays across all nodes in the spatial planning graph for a set of future time windows. When using predictions in a modified path planner, simulation experiments using production data show 4. 4% average improvement in throughput performance versus without predictions.

Details

AAAI Conference 2023 Conference Paper

Soft Target-Enhanced Matching Framework for Deep Entity Matching

Wenzhou Dou
Derong Shen
Xiangmin Zhou
Tiezheng Nie
Yue Kou
Hang Cui
Ge Yu

Deep Entity Matching (EM) is one of the core research topics in data integration. Typical existing works construct EM models by training deep neural networks (DNNs) based on the training samples with onehot labels. However, these sharp supervision signals of onehot labels harm the generalization of EM models, causing them to overfit the training samples and perform badly in unseen datasets. To solve this problem, we first propose that the challenge of training a well-generalized EM model lies in achieving the compromise between fitting the training samples and imposing regularization, i.e., the bias-variance tradeoff. Then, we propose a novel Soft Target-EnhAnced Matching (Steam) framework, which exploits the automatically generated soft targets as label-wise regularizers to constrain the model training. Specifically, Steam regards the EM model trained in previous iteration as a virtual teacher and takes its softened output as the extra regularizer to train the EM model in the current iteration. As such, Steam effectively calibrates the obtained EM model, achieving the bias-variance tradeoff without any additional computational cost. We conduct extensive experiments over open datasets and the results show that our proposed Steam outperforms the state-of-the-art EM approaches in terms of effectiveness and label efficiency.

PDF Details DOI

TIST Journal 2020 Journal Article

On Representation Learning for Road Networks

Meng-Xiang Wang
Wang-Chien Lee
Tao-Yang Fu
Ge Yu

Informative representation of road networks is essential to a wide variety of applications on intelligent transportation systems. In this article, we design a new learning framework, called Representation Learning for Road Networks (RLRN), which explores various intrinsic properties of road networks to learn embeddings of intersections and road segments in road networks. To implement the RLRN framework, we propose a new neural network model, namely Road Network to Vector (RN2Vec), to learn embeddings of intersections and road segments jointly by exploring geo-locality and homogeneity of them, topological structure of the road networks, and moving behaviors of road users. In addition to model design, issues involving data preparation for model training are examined. We evaluate the learned embeddings via extensive experiments on several real-world datasets using different downstream test cases, including node/edge classification and travel time estimation. Experimental results show that the proposed RN2Vec robustly outperforms existing methods, including (i) Feature-based methods: raw features and principal components analysis (PCA); (ii) Network embedding methods: DeepWalk, LINE, and Node2vec; and (iii) Features + Network structure-based methods: network embeddings and PCA, graph convolutional networks, and graph attention networks. RN2Vec significantly outperforms all of them in terms of F1-score in classifying traffic signals (11.96% to 16.86%) and crossings (11.36% to 16.67%) on intersections and in classifying avenue (10.56% to 15.43%) and street (11.54% to 16.07%) on road segments, as well as in terms of Mean Absolute Error in travel time estimation (17.01% to 23.58%).

Details DOI

AAAI Conference 2019 Conference Paper

Linear Kernel Tests via Empirical Likelihood for High-Dimensional Data

Lizhong Ding
Zhi Liu
Yu Li
Shizhong Liao
Yong Liu
Peng Yang
Ge Yu
Ling Shao

We propose a framework for analyzing and comparing distributions without imposing any parametric assumptions via empirical likelihood methods. Our framework is used to study two fundamental statistical test problems: the two-sample test and the goodness-of-fit test. For the two-sample test, we need to determine whether two groups of samples are from different distributions; for the goodness-of-fit test, we examine how likely it is that a set of samples is generated from a known target distribution. Specifically, we propose empirical likelihood ratio (ELR) statistics for the two-sample test and the goodness-of-fit test, both of which are of linear time complexity and show higher power (i. e. , the probability of correctly rejecting the null hypothesis) than the existing linear statistics for high-dimensional data. We prove the nonparametric Wilks’ theorems for the ELR statistics, which illustrate that the limiting distributions of the proposed ELR statistics are chi-square distributions. With these limiting distributions, we can avoid bootstraps or simulations to determine the threshold for rejecting the null hypothesis, which makes the ELR statistics more efficient than the recently proposed linear statistic, finite set Stein discrepancy (FSSD). We also prove the consistency of the ELR statistics, which guarantees that the test power goes to 1 as the number of samples goes to infinity. In addition, we experimentally demonstrate and theoretically analyze that FSSD has poor performance or even fails to test for high-dimensional data. Finally, we conduct a series of experiments to evaluate the performance of our ELR statistics as compared to state-of-the-art linear statistics.

PDF Details

IJCAI Conference 2015 Conference Paper

Personalized Sentiment Classification Based on Latent Individuality of Microblog Users

Kaisong Song
Shi Feng
Wei Gao
Daling Wang
Ge Yu
Kam-Fai Wong

Sentiment expression in microblog posts often reflects user’s specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this paper, we propose a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms stateof-the-art baseline algorithms with large margins.

PDF Details

IROS Conference 2013 Conference Paper

Accelerating optimization-based haptic rendering by parallel quadratic programming method

Ge Yu
Dangxiao Wang
Yuru Zhang

It is a challenging problem to achieve fast and realistic six degree-of-freedom (DOF) haptic simulation of scenarios involving large number of multi-region contacts. In this paper, we propose an optimization-based constrained method enhanced by parallel quadratic programming to solve the rendering problem. Hierarchical sphere-tree models are used to represent the moving haptic tool and its surrounding static objects. Given a moving graphic tool as the avatar of the haptic tool in the virtual environment, we compute its quasi-static motion by solving a configuration-based optimization. Instead of using traditional active-set method, we transform the original optimization problem into its dual problem and solve the optimum about the graphic tool using a parallel quadratic programming method. Our algorithm has been implemented with a 6-DoF Phantom Premium 3. 0. We validate the proposed algorithm in several benchmarks involving complex, large-region contacts. The results demonstrate that the proposed method can achieve a two to three times speed improvement than the active-set method. A further speed-up for haptic rendering may be achieved by the parallel implementation on parallel processor such as graphic processing units.

Details

IROS Conference 2012 Conference Paper

Six degree-of-freedom haptic simulation of sharp geometric features using a hybrid sphere-tree model

Ge Yu
Dangxiao Wang
Yuru Zhang
Xin Zhang

Subtle force feelings caused by contacts at sharp geometric features are necessary to achieve high-fidelity haptic rendering. It is a challenging problem to achieve six degree-of-freedom (6-DOF) haptic simulation with sharp features for multi-region contacts scenario. We propose a configuration-based optimization method using a hybrid sphere-tree model to compute constraint-based collision response. Based on the variance of dihedral angle between adjacent triangles, an original triangle mesh of the simulated object is segmented into a hybrid sphere-tree model, i. e. a hierarchical sphere-tree for global shape and several linear-lists of spheres for local areas with sharp features. In each local area with sharp features, we first identify those spheres which radius is larger than a pre-defined perceptual threshold. Then these spheres are divided into a linear list of smaller spheres by a splitting method. The experiment results on a sphere-cube interaction and a spline-shaped peg-hole interaction validate that the proposed method can simulate a subtle force direction change when sliding contact occurs across the sharp edges. Non-penetration between the two objects can be maintained for multi-region contacts scenario. The haptic rendering rate is over 1kHz and the interaction is stable.

Details