Searcharxiv⌕ Search

arXiv subjects

Yao Cheng

Publications and source records attributed to Yao Cheng.

At least 37 records · Page 2Linked to original sources
arXiv2025

Intelligent Spatial Perception by Building Hierarchical 3D Scene Graphs for Indoor Scenarios with the Help of LLMs

This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to construct hierarchical 3D Scene Graphs (3DSGs) for indoor scenarios. The proposed framework constructs 3DSGs consisting of a fundamental layer with rich metric-semantic information, an object layer featuring precise point-cloud representation of object nodes as well as visual descriptors, and higher layers of room, floor, and building nodes. Thanks to the innovative application of LLMs, not only object nodes but also nodes of higher layers, e.g., room nodes, are annotated in an intelligent and accurate manner. A polling mechanism for room classification using LLMs is proposed to enhance the accuracy and reliability of the room node annotation. Thorough numerical experiments demonstrate the system's ability to integrate semantic descriptions with geometric data, creating an accurate and comprehensive representation of the environment instrumental for context-aware navigation and task planning.

cs.RO↗
arXiv2024

LAMOST J171013+532646: a detached short-period non-eclipsing hot subdwarf + white dwarf binary

We present an analysis of LAMOST J171013.211+532646.04 (hereafter J1710), a binary system comprising a hot subdwarf B star (sdB) and a white dwarf (WD) companion. Multi-epoch spectroscopy reveals an orbital period of 109.20279 minutes, consistent with TESS and ZTF photometric data, marking it as the sixth detached system known to harbor a WD companion with a period less than two hours. J1710 is remarkably close to Earth, situated at a distance of only \(350.68^{+4.20}_{-4.21} \, \mathrm{pc}\), with a GAIA G-band magnitude of 12.59, rendering it conducive for continuous observations. The spectral temperature is around 25164 K, in agreement with SED fitting results (\(25301^{+839}_{-743} \, \mathrm{K}\)). The TESS light curve displays ellipsoidal variation and Doppler beaming without eclipsing features. Through fitting the TESS light curve using the Wilson-Devinney code, we determined the masses for the sdB (\(M_1 = 0.44^{+0.06}_{-0.07} \, M_{\odot}\)) and the compact object (\(M_2 = 0.54^{+0.10}_{-0.07} \, M_{\odot}\)), with the compact object likely being a WD. Furthermore, MESA models suggest that the sdB, with a helium core mass of 0.431 \(M_{\odot}\) and a hydrogen envelope mass of \(1.3 \times 10^{-3}\, M_{\odot}\), is in the early helium main-sequence phase. The MESA binary evolution shows that the J1710 system is expected to evolve into a double white dwarf system, making it an important source of low-frequency gravitational waves.

astro-ph.SR↗
arXiv2024

An optimization-free approximation Framework for Connected and Automated Vehicles Eco-Trajectory Planning Under limited computing capacity

The trajectory planning problem (TPP) has become increasingly crucial in the research of next-generation transportation systems, but it presents challenges due to the non-linearity of its constraints. One specific case within TPP, namely the Eco-trajectory Planning Problem (EPP), poses even greater computational difficulties due to its nonlinear, high-order, and non-convex objective function. This paper proposes an optimization-free framework to address the eco-trajectory planning problem of connected and automated vehicles (CAVs) in the straight-driving scenario. The framework consists of an offline module and an online module. In the offline module, an optimal eco-trajectory batch is constructed by solving a sequence of simplified optimization problems to minimize fuel consumption, considering various initial and terminal system states. Each candidate trajectory in the batch yields the lowest fuel consumption subject to a specific travel time from the vehicle entry to the departure from the intersection. In the online module, dynamic trajectory planning algorithms based on different scenarios are provided. Both algorithms greatly improve the computational efficiency of planning and only suffer from a limited extent of optimality losses through a batch-based selection process because optimization and calculation are pre-computed in the offline module. The latter algorithm can also handle possible emergencies and prediction errors. Numerical tests are presented and discussed to evaluate the computational quality and efficiency of the optimization-free approximation framework under a mixed-traffic flow environment that incorporates human-driving vehicles (HDV) and connected and automated vehicles (CAV) with different market penetration rates (MPR).

math.OC↗
arXiv2024

Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes

Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently demonstrated excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) ignore the problems of missing attributes, inaccurate attributes and scarce labels for nodes, which limits their expressiveness. In this paper, we propose a generative self-supervised model GraMI to address these issues simultaneously. Specifically, GraMI first initializes all the nodes in the graph with a low-dimensional representation matrix. After that, based on the variational graph autoencoder framework, GraMI learns both node-level and attribute-level embeddings in the encoder, which can provide fine-grained semantic information to construct node attributes. In the decoder, GraMI reconstructs both links and attributes. Instead of directly reconstructing raw features for attributed nodes, GraMI generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed to leverage accurate attributes. In this way, GraMI can not only complete informative features for non-attributed nodes, but rectify inaccurate ones for attributed nodes. Finally, we conduct extensive experiments to show the superiority of GraMI in tackling HINs with missing and inaccurate attributes.

cs.LG↗
arXiv2024

Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning

Graph neural network (GNN) has captured wide attention due to its capability of graph representation learning for graph-structured data. However, the distributed data silos limit the performance of GNN. Vertical federated learning (VFL), an emerging technique to process distributed data, successfully makes GNN possible to handle the distributed graph-structured data. Despite the prosperous development of vertical federated graph learning (VFGL), the robustness of VFGL against the adversarial attack has not been explored yet. Although numerous adversarial attacks against centralized GNNs are proposed, their attack performance is challenged in the VFGL scenario. To the best of our knowledge, this is the first work to explore the adversarial attack against VFGL. A query-efficient hybrid adversarial attack framework is proposed to significantly improve the centralized adversarial attacks against VFGL, denoted as NA2, short for Neuron-based Adversarial Attack. Specifically, a malicious client manipulates its local training data to improve its contribution in a stealthy fashion. Then a shadow model is established based on the manipulated data to simulate the behavior of the server model in VFGL. As a result, the shadow model can improve the attack success rate of various centralized attacks with a few queries. Extensive experiments on five real-world benchmarks demonstrate that NA2 improves the performance of the centralized adversarial attacks against VFGL, achieving state-of-the-art performance even under potential adaptive defense where the defender knows the attack method. Additionally, we provide interpretable experiments of the effectiveness of NA2 via sensitive neurons identification and visualization of t-SNE.

cs.LG↗
arXiv2024

ROADFIRST: A Comprehensive Enhancement of the Systemic Approach to Safety for Improved Risk Factor Identification and Evaluation

Many agencies have adopted the FHWA-recommended systemic approach to traffic safety, an essential supplement to the traditional hotspot crash analysis which develops region-wide safety projects based on identified risk factors. However, this approach narrows analysis to specific crash and facility types. This specification causes inefficient use of crash and inventory data as well as non-comprehensive risk evaluation and countermeasure selection for each location. To improve the comprehensiveness of the systemic approach to safety, we develop an enhanced process, ROADFIRST, that allows users to identify potential crash types and contributing factors at any location. As the knowledge base for such a process, crash types and contributing factors are analyzed with respect to features of interest, including both dynamic and static traffic-related features, using Random Forest and analyzed with the SHapley Additive exPlanations (SHAP) analysis. We identify and rank features impacting the likelihood of three sample contributing factors, namely alcohol-impaired driving, distracted driving, and speeding, according to crash and road inventory data from North Carolina, and quantify state-wide road segment risk for each contributing factor. The introduced models and methods serve as a sample for the further development of ROADFIRST by state and local agencies, which benefits the planning of more comprehensive region-wide safety improvement projects.

cs.LG↗
arXiv2024

A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions

Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many real-world applications. Meanwhile, increasing efforts have been made to advance learning from graphs with heterophily. Various graph heterophily measures, benchmark datasets, and learning paradigms are emerging rapidly. In this survey, we comprehensively review existing works on learning from graphs with heterophily. First, we overview over 500 publications, of which more than 340 are directly related to heterophilic graphs. After that, we survey existing metrics of graph heterophily and list recent benchmark datasets. Further, we systematically categorize existing methods based on a hierarchical taxonomy including GNN models, learning paradigms and practical applications. In addition, broader topics related to graph heterophily are also included. Finally, we discuss the primary challenges of existing studies and highlight promising avenues for future research.

cs.SI↗
arXiv2024

Optimal balanced-norm error estimate of the LDG method for reaction-diffusion problems II: the two-dimensional case with layer-upwind flux

A singularly perturbed reaction-diffusion problem posed on the unit square in $\mathbb{R}^2$ is solved numerically by a local discontinuous Galerkin (LDG) finite element method. Typical solutions of this class of 2D problems exhibit boundary layers along the sides of the domain; these layers generally cause difficulties for numerical methods. Our LDG method handles the boundary layers by using a Shishkin mesh and also introducing the new concept of a ``layer-upwind flux" -- a discrete flux whose values are chosen on the fine mesh (which lies inside the boundary layers) in the direction where the layer weakens. On the coarse mesh, one can use a standard central flux. No penalty terms are needed with these fluxes, unlike many other variants of the LDG method. Our choice of discrete flux makes it feasible to derive an optimal-order error analysis in a balanced norm; this norm is stronger than the usual energy norm and is a more appropriate measure for errors in computed solutions for singularly perturbed reaction-diffusion problems. It will be proved that the LDG method is usually convergent of order $O((N^{-1}\ln N)^{k+1})$ in the balanced norm, where $N$ is the number of mesh intervals in each coordinate direction and tensor-product piecewise polynomials of degree~$k$ in each coordinate variable are used in the LDG method. This result is the first of its kind for the LDG method applied to this class of problem and is optimal for convergence on a Shishkin mesh. Its sharpness is confirmed by numerical experiments.

math.NA↗
arXiv2024

Resurrecting Label Propagation for Graphs with Heterophily and Label Noise

Label noise is a common challenge in large datasets, as it can significantly degrade the generalization ability of deep neural networks. Most existing studies focus on noisy labels in computer vision; however, graph models encompass both node features and graph topology as input, and become more susceptible to label noise through message-passing mechanisms. Recently, only a few works have been proposed to tackle the label noise on graphs. One significant limitation is that they operate under the assumption that the graph exhibits homophily and that the labels are distributed smoothly. However, real-world graphs can exhibit varying degrees of heterophily, or even be dominated by heterophily, which results in the inadequacy of the current methods. In this paper, we study graph label noise in the context of arbitrary heterophily, with the aim of rectifying noisy labels and assigning labels to previously unlabeled nodes. We begin by conducting two empirical analyses to explore the impact of graph homophily on graph label noise. Following observations, we propose a efficient algorithm, denoted as $R^{2}LP$. Specifically, $R^{2}LP$ is an iterative algorithm with three steps: (1) reconstruct the graph to recover the homophily property, (2) utilize label propagation to rectify the noisy labels, (3) select high-confidence labels to retain for the next iteration. By iterating these steps, we obtain a set of correct labels, ultimately achieving high accuracy in the node classification task. The theoretical analysis is also provided to demonstrate its remarkable denoising effect. Finally, we perform experiments on ten benchmark datasets with different levels of graph heterophily and various types of noise. In these experiments, we compare the performance of $R^{2}LP$ against ten typical baseline methods. Our results illustrate the superior performance of the proposed $R^{2}LP$.

cs.LG↗
arXiv2024

G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning

Commonsense question answering has demonstrated considerable potential across various applications like assistants and social robots. Although fully fine-tuned pre-trained Language Models(LM) have achieved remarkable performance in commonsense reasoning, their tendency to excessively prioritize textual information hampers the precise transfer of structural knowledge and undermines interpretability. Some studies have explored combining LMs with Knowledge Graphs(KGs) by coarsely fusing the two modalities to perform Graph Neural Network(GNN)-based reasoning that lacks a profound interaction between heterogeneous modalities. In this paper, we propose a novel Graph-based Structure-Aware Prompt Learning Model for commonsense reasoning, named G-SAP, aiming to maintain a balance between heterogeneous knowledge and enhance the cross-modal interaction within the LM+GNNs model. In particular, an evidence graph is constructed by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and Cambridge Dictionary to boost the performance. Afterward, a structure-aware frozen PLM is employed to fully incorporate the structured and textual information from the evidence graph, where the generation of prompts is driven by graph entities and relations. Finally, a heterogeneous message-passing reasoning module is used to facilitate deep interaction of knowledge between the LM and graph-based networks. Empirical validation, conducted through extensive experiments on three benchmark datasets, demonstrates the notable performance of the proposed model. The results reveal a significant advancement over the existing models, especially, with 6.12% improvement over the SoTA LM+GNNs model on the OpenbookQA dataset.

cs.CL↗
arXiv2024

Learn2Talk: 3D Talking Face Learns from 2D Talking Face

Speech-driven facial animation methods usually contain two main classes, 3D and 2D talking face, both of which attract considerable research attention in recent years. However, to the best of our knowledge, the research on 3D talking face does not go deeper as 2D talking face, in the aspect of lip-synchronization (lip-sync) and speech perception. To mind the gap between the two sub-fields, we propose a learning framework named Learn2Talk, which can construct a better 3D talking face network by exploiting two expertise points from the field of 2D talking face. Firstly, inspired by the audio-video sync network, a 3D sync-lip expert model is devised for the pursuit of lip-sync between audio and 3D facial motion. Secondly, a teacher model selected from 2D talking face methods is used to guide the training of the audio-to-3D motions regression network to yield more 3D vertex accuracy. Extensive experiments show the advantages of the proposed framework in terms of lip-sync, vertex accuracy and speech perception, compared with state-of-the-arts. Finally, we show two applications of the proposed framework: audio-visual speech recognition and speech-driven 3D Gaussian Splatting based avatar animation.

cs.CV↗
arXiv2024

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks. These tasks require agents to end-to-end solving complex tasks by interacting with an execution environment. This benchmark contains DAEval, a dataset consisting of 257 data analysis questions derived from 52 CSV files, and an agent framework which incorporates LLMs to serve as data analysis agents for both serving and evaluation. Since data analysis questions are often open-ended and hard to evaluate without human supervision, we adopt a format-prompting technique to convert each question into a closed-form format so that they can be automatically evaluated. Our extensive benchmarking of 34 LLMs uncovers the current challenges encountered in data analysis tasks. In addition, building on top of our agent framework, we develop a specialized agent, DAAgent, which surpasses GPT-3.5 by 3.9% on DABench. Evaluation datasets and toolkits for InfiAgent-DABench are released at https://github.com/InfiAgent/InfiAgent .

cs.CL↗
arXiv2023

Super-resolution Reconstruction of Single Image for Latent features

Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features. This challenge can lead to issues such as model collapse, lack of rich details and texture features in the reconstructed HR images, and excessive time consumption for model sampling. To address these problems, this paper proposes a Latent Feature-oriented Diffusion Probability Model (LDDPM). First, we designed a conditional encoder capable of effectively encoding LR images, reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images. We then employed a normalized flow and multimodal adversarial training, learning from complex multimodal distributions, to model the denoising distribution. Doing so boosts the generative modeling capabilities within a minimal number of sampling steps. Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics, providing a fresh perspective for tackling SISR tasks.

eess.IV↗
arXiv2023

Prioritized Propagation in Graph Neural Networks

Graph neural networks (GNNs) have recently received significant attention. Learning node-wise message propagation in GNNs aims to set personalized propagation steps for different nodes in the graph. Despite the success, existing methods ignore node priority that can be reflected by node influence and heterophily. In this paper, we propose a versatile framework PPro, which can be integrated with most existing GNN models and aim to learn prioritized node-wise message propagation in GNNs. Specifically, the framework consists of three components: a backbone GNN model, a propagation controller to determine the optimal propagation steps for nodes, and a weight controller to compute the priority scores for nodes. We design a mutually enhanced mechanism to compute node priority, optimal propagation step and label prediction. We also propose an alternative optimization strategy to learn the parameters in the backbone GNN model and two parametric controllers. We conduct extensive experiments to compare our framework with other 11 state-of-the-art competitors on 8 benchmark datasets. Experimental results show that our framework can lead to superior performance in terms of propagation strategies and node representations.

cs.LG↗
arXiv2023

Orbital parameters for an ELM white dwarf with a white dwarf companion: LAMOST J033847.06+413424.2

Double white dwarf systems are of great astrophysical importance in the field of gravitational wave and Type Ia supernova. While the binary fraction of CO core white dwarf is about a few percents, the extremely low mass white dwarfs are all thought to be within binary systems. In this work, we report the orbital solution of a double degenerate system: J033847.06+413424.24, an extremely low mass He core white dwarf orbiting a CO core white dwarf. With LAMOST and P200, time domain spectroscopic observations have been made and spectral atmosphere parameters are estimated to be $T_{\rm eff}\sim22500$ K and log $g\sim5.6$ dex. Combining Gaia parallax, 3D extinction, and evolution tracks, we estimate a radius of $\sim0.12$ $R_{\odot}$ and a mass of $\sim0.22$ $M_{\odot}$. With the 37 single exposure spectra, the radial velocities are measured and the orbital parameters are estimated to be $P=0.1253132(1)$ days, $K1=289\pm4$ km/s and $V_{sys}=-41\pm3$ km/s. The radial velocity based system ephemeris is also provided. The light curves from several photometric surveys show no orbital modulation. The orbital solution suggests that the invisible companion has a minimum mass of about 0.60 $M_{\odot}$ and is $\sim0.79$ $M_{\odot}$ for an inclination of $60.0^{\circ}$, indicating most probably a CO core white dwarf. The system is expected to merge in about 1 Gyr. With present period and distance ($\sim596$ pc) it can not irradiate strong enough gravitational wave for LISA. More double degenerate systems are expected to be discovered and parameterized as the LAMOST survey goes on.

astro-ph.SR↗
arXiv2023

Graph Self-Contrast Representation Learning

Graph contrastive learning (GCL) has recently emerged as a promising approach for graph representation learning. Some existing methods adopt the 1-vs-K scheme to construct one positive and K negative samples for each graph, but it is difficult to set K. For those methods that do not use negative samples, it is often necessary to add additional strategies to avoid model collapse, which could only alleviate the problem to some extent. All these drawbacks will undoubtedly have an adverse impact on the generalizability and efficiency of the model. In this paper, to address these issues, we propose a novel graph self-contrast framework GraphSC, which only uses one positive and one negative sample, and chooses triplet loss as the objective. Specifically, self-contrast has two implications. First, GraphSC generates both positive and negative views of a graph sample from the graph itself via graph augmentation functions of various intensities, and use them for self-contrast. Second, GraphSC uses Hilbert-Schmidt Independence Criterion (HSIC) to factorize the representations into multiple factors and proposes a masked self-contrast mechanism to better separate positive and negative samples. Further, Since the triplet loss only optimizes the relative distance between the anchor and its positive/negative samples, it is difficult to ensure the absolute distance between the anchor and positive sample. Therefore, we explicitly reduced the absolute distance between the anchor and positive sample to accelerate convergence. Finally, we conduct extensive experiments to evaluate the performance of GraphSC against 19 other state-of-the-art methods in both unsupervised and transfer learning settings.

cs.LG↗
arXiv2023

Edge Deep Learning Model Protection via Neuron Authorization

With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things. Edge device models are generally considered as valuable intellectual properties that are worth for careful protection. Unfortunately, these models have a great risk of being stolen or illegally copied. The existing model protections using encryption algorithms are suffered from high computation overhead which is not practical due to the limited computing capacity on edge devices. In this work, we propose a light-weight, practical, and general Edge device model Pro tection method at neuron level, denoted as EdgePro. Specifically, we select several neurons as authorization neurons and set their activation values to locking values and scale the neuron outputs as the "asswords" during training. EdgePro protects the model by ensuring it can only work correctly when the "passwords" are met, at the cost of encrypting and storing the information of the "passwords" instead of the whole model. Extensive experimental results indicate that EdgePro can work well on the task of protecting on datasets with different modes. The inference time increase of EdgePro is only 60% of state-of-the-art methods, and the accuracy loss is less than 1%. Additionally, EdgePro is robust against adaptive attacks including fine-tuning and pruning, which makes it more practical in real-world applications. EdgePro is also open sourced to facilitate future research: https://github.com/Leon022/Edg

cs.CR↗