arXiv subjects

Yansong Wang

Publications and source records attributed to Yansong Wang.

At least 19 recordsLinked to original sources

arXiv2026

DyG$^2$T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer

Modeling object dynamics from limited visual observations is a fundamental problem for enabling accurate motion trajectory prediction in embodied interaction scenarios. Existing dynamics modeling methods first compress reconstructed particle representations into sparse Key Points and model their evolution using locally constrained interactions, thereby discarding fine-grained local details and obscuring discriminative interaction modeling across spatial and temporal scales, leading to drifting trajectories and inaccurate appearance prediction. To tackle these issues, we propose DyG$^2$T, a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations and modeling multi-scale interaction over particle graphs. Spatially, DyG$^2$T enriches each Key Point by aggregating neighboring raw particle positions to recover fine-grained local details, while explicitly encoding relative offsets among Key Points to enhance geometric structure perception. Temporally, we introduce a Temporal Disentangling Network (TDN) to identify dominant cross-frame variations in latent space and amplify inter-frame differences, yielding temporally discriminative representations that are subsequently aggregated via Temporal Attention to capture frame-wise temporal evolution cues. For comprehensive interaction modeling, a Particle Graph Transformer leverages global attention to preserve discriminative long-range dependencies among Key Points, mitigating representation homogenization induced by locality-constrained modeling and providing a robust basis for accurate trajectory prediction. Experiments on both synthetic and real-world datasets demonstrate that DyG$^2$T achieves accurate dynamics modeling and reasoning, and exhibits strong cross-object and real-world generalization.

cs.CV↗

arXiv2026

Motif-Mamba: network motif improved mamba for long-range sequence modeling

Efficient long-sequence modeling remains a central challenge for large language models, as self-attention scales quadratically with sequence length. Mamba offers a linear-time alternative through selective state space recurrence, but its predominantly diagonal state transitions restrict explicit interactions among state dimensions. We propose Motif-Mamba, a structured state space model that augments Mamba with a motif-constrained low-rank recurrent pathway. Inspired by the dynamics of three-node network motifs, the proposed pathway projects hidden states into a compact dynamical subspace, imposes motif-guided interactions, and maps the resulting dynamics back to the original state space. This design enhances cross-dimensional communication while preserving the linear-time recurrent structure of Mamba. Experiments on long-sequence extrapolation, language modeling benchmarks, and brain--computer interface decoding show consistent improvements over Mamba backbones, suggesting that motif-guided low-rank dynamics provide an effective structural prior for long-range sequence modeling.

cs.AI↗

arXiv2026

PDSL: Propagation Dynamics Aware Framework for Source Localization

Source localization is a representative inverse inference task in information propagation, aiming to identify the source node or node set that triggers the propagation results based on the observed information. A primary challenge is quantifying the inherent uncertainty between observed outcomes and potential sources. Although deep generative models have partially mitigated this issue, most existing approaches primarily focus on uncertainty induced by network topology, attempting to learn a direct mapping from propagation outcomes to sources based on network structure, while overlooking the additional uncertainty stemming from the highly stochastic nature of the propagation process. To address this limitation, we propose a Propagation Dynamics aware framework for Source Localization (PDSL), a novel method that integrates a deep generative model with propagation dynamics to approximate the source distribution and explicitly mitigate uncertainty arising from diffusion stochasticity. Moreover, we employ Graph Neural Ordinary Differential Equations to model the continuous dynamics of diffusion processes without relying on a predefined diffusion mechanism. Additionally, a matching mechanism is designed to extract relevant data blocks that enhance source generation reliability. Comprehensive experiments on both synthetic and real-world diffusion datasets demonstrate the superior performance of the proposed framework across diverse application scenarios.

cs.SI↗

arXiv2026

GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Models

Reconstructing a renderable 3D model from images is a useful but challenging task. Recent feedforward 3D reconstruction methods have demonstrated remarkable success in efficiently recovering geometry, but still cannot accurately model the complex appearances of these 3D reconstructed models. Recent diffusion-based generative models can synthesize realistic images or videos of an object using reference images without explicitly modeling its appearance, which provides a promising direction for object rendering, but lacks accurate control over the viewpoints. In this paper, we propose GO-Renderer, a unified framework integrating the reconstructed 3D proxies to guide the video generative models to achieve high-quality object rendering on arbitrary viewpoints under arbitrary lighting conditions. Our method not only enjoys the accurate viewpoint control using the reconstructed 3D proxy but also enables high-quality rendering in different lighting environments using diffusion generative models without explicitly modeling complex materials and lighting. Extensive experiments demonstrate that GO-Renderer achieves state-of-the-art performance across the object rendering tasks, including synthesizing images on new viewpoints, rendering the objects in a novel lighting environment, and inserting an object into an existing video.

cs.CV↗

arXiv2025

Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation

As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact representations that preserve both topological structure and robustness profile, enabling efficient and reliable evaluation. We propose Cutter, a dual-agent reinforcement learning framework composed of a Vital Detection Agent (VDA) and a Redundancy Detection Agent (RDA), which collaboratively identify structurally vital and redundant nodes for guided compression. Cutter incorporates three key strategies to enhance learning efficiency and compression quality: trajectory-level reward shaping to transform sparse trajectory returns into dense, policy-equivalent learning signals; prototype-based shaping to guide decisions using behavioral patterns from both high- and low-return trajectories; and cross-agent imitation to enable safer and more transferable exploration. Experiments on multiple real-world graphs demonstrate that Cutter generates compressed graphs that retain essential static topological properties and exhibit robustness degradation trends highly consistent with the original graphs under various attack scenarios, thereby significantly improving evaluation efficiency without compromising assessment fidelity.

cs.LG↗

arXiv2025

Generative Data Augmentation in Graph Contrastive Learning for Recommendation

Recommendation systems have become indispensable in various online platforms, from e-commerce to streaming services. A fundamental challenge in this domain is learning effective embeddings from sparse user-item interactions. While contrastive learning has recently emerged as a promising solution to this issue, generating augmented views for contrastive learning through most existing random data augmentation methods often leads to the alteration of original semantic information. In this paper, we propose a novel framework, GDA4Rec (Generative Data Augmentation in graph contrastive learning for Recommendation) to generate high-quality augmented views and provide robust self-supervised signals. Specifically, we employ a noise generation module that leverages deep generative models to approximate the distribution of original data for data augmentation. Additionally, GDA4Rec further extracts an item complement matrix to characterize the latent correlations between items and provide additional self-supervised signals. Lastly, a joint objective that integrates recommendation, data augmentation and contrastive learning is used to enforce the model to learn more effective and informative embeddings. Extensive experiments are conducted on three public datasets to demonstrate the superiority of the model. The code is available at: https://github.com/MrYansong/GDA4Rec.

cs.IR↗

arXiv2025

Collaborative Prediction: To Join or To Disjoin Datasets

With the recent rise of generative Artificial Intelligence (AI), the need of selecting high-quality dataset to improve machine learning models has garnered increasing attention. However, some part of this topic remains underexplored, even for simple prediction models. In this work, we study the problem of developing practical algorithms that select appropriate dataset to minimize population loss of our prediction model with high probability. Broadly speaking, we investigate when datasets from different sources can be effectively merged to enhance the predictive model's performance, and propose a practical algorithm with theoretical guarantees. By leveraging an oracle inequality and data-driven estimators, the algorithm reduces population loss with high probability. Numerical experiments demonstrate its effectiveness in both standard linear regression and broader machine learning applications. Code is available at https://github.com/kkrokii/collaborative_prediction.

stat.ML↗

arXiv2025

WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation

The UAV technology is gradually maturing and can provide extremely powerful support for smart agriculture and precise monitoring. Currently, there is no dataset related to green walnuts in the field of agricultural computer vision. Thus, in order to promote the algorithm design in the field of agricultural computer vision, we used UAV to collect remote-sensing data from 8 walnut sample plots. Considering that green walnuts are subject to various lighting conditions and occlusion, we constructed a large-scale dataset with a higher-granularity of target features - WalnutData. This dataset contains a total of 30,240 images and 706,208 instances, and there are 4 target categories: being illuminated by frontal light and unoccluded (A1), being backlit and unoccluded (A2), being illuminated by frontal light and occluded (B1), and being backlit and occluded (B2). Subsequently, we evaluated many mainstream algorithms on WalnutData and used these evaluation results as the baseline standard. The dataset and all evaluation results can be obtained at https://github.com/1wuming/WalnutData.

cs.CV↗

arXiv2024

Research on signalized intersection mixed traffic flow platoon control method considering Backward-looking effect

Connected and Autonomous Vehicles (CAVs) technology facilitates the advancement of intelligent transportation. However, intelligent control techniques for mixed traffic flow at signalized intersections involving both CAVs and Human-Driven Vehicles (HDVs) require further investigation into the impact of backward-looking effect. This paper proposes the concept of 1+n+1 mixed platoon considering the backward-looking effect, consisting of one leading CAV, n following HDVs, and one trailing CAV. The leading and trailing CAVs collectively guide the movement of intermediate HDVs at intersections, forming an optimal control framework for platoon-based CAVs at signalized intersections. Initially, a linearized dynamic model for the 1+n+1 mixed platoon is established and compared with a benchmark model focusing solely on controlling the lead vehicle. Subsequently, constraints are formulated for the optimal control framework, aiming to enhance overall intersection traffic efficiency and fuel economy by directly controlling the leading and trailing CAVs in the platoon. Finally, extensive numerical simulations compare vehicle throughput and fuel consumption at signalized intersections under different mixed platoon control methods, validating that considering both front and backward-looking effects in the mixed platoon control method outperforms traditional methods focusing solely on the lead CAV.

physics.app-ph↗

arXiv2024

Hierarchical Space-Time Attention for Micro-Expression Recognition

Micro-expression recognition (MER) aims to recognize the short and subtle facial movements from the Micro-expression (ME) video clips, which reveal real emotions. Recent MER methods mostly only utilize special frames from ME video clips or extract optical flow from these special frames. However, they neglect the relationship between movements and space-time, while facial cues are hidden within these relationships. To solve this issue, we propose the Hierarchical Space-Time Attention (HSTA). Specifically, we first process ME video frames and special frames or data parallelly by our cascaded Unimodal Space-Time Attention (USTA) to establish connections between subtle facial movements and specific facial areas. Then, we design Crossmodal Space-Time Attention (CSTA) to achieve a higher-quality fusion for crossmodal data. Finally, we hierarchically integrate USTA and CSTA to grasp the deeper facial cues. Our model emphasizes temporal modeling without neglecting the processing of special data, and it fuses the contents in different modalities while maintaining their respective uniqueness. Extensive experiments on the four benchmarks show the effectiveness of our proposed HSTA. Specifically, compared with the latest method on the CASME3 dataset, it achieves about 3% score improvement in seven-category classification.

cs.CV↗

arXiv2024

GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation

Graph Neural Networks (GNNs) have emerged as the most powerful weapon for various graph tasks due to the message-passing mechanism's great local information aggregation ability. However, over-smoothing has always hindered GNNs from going deeper and capturing multi-hop neighbors. Unlike GNNs, Transformers can model global information and multi-hop interactions via multi-head self-attention and a proper Transformer structure can show more immunity to the over-smoothing problem. So, can we propose a novel framework to combine GNN and Transformer, integrating both GNN's local information aggregation and Transformer's global information modeling ability to eliminate the over-smoothing problem? To realize this, this paper proposes a collaborative learning scheme for GNN-Transformer and constructs GTC architecture. GTC leverages the GNN and Transformer branch to encode node information from different views respectively, and establishes contrastive learning tasks based on the encoded cross-view information to realize self-supervised heterogeneous graph representation. For the Transformer branch, we propose Metapath-aware Hop2Token and CG-Hetphormer, which can cooperate with GNN to attentively encode neighborhood information from different levels. As far as we know, this is the first attempt in the field of graph representation learning to utilize both GNN and Transformer to collaboratively capture different view information and conduct cross-view contrastive learning. The experiments on real datasets show that GTC exhibits superior performance compared with state-of-the-art methods. Codes can be available at https://github.com/PHD-lanyu/GTC.

cs.LG↗

arXiv2024

SpikeGraphormer: A High-Performance Graph Transformer with Spiking Graph Attention

Recently, Graph Transformers have emerged as a promising solution to alleviate the inherent limitations of Graph Neural Networks (GNNs) and enhance graph representation performance. Unfortunately, Graph Transformers are computationally expensive due to the quadratic complexity inherent in self-attention when applied over large-scale graphs, especially for node tasks. In contrast, spiking neural networks (SNNs), with event-driven and binary spikes properties, can perform energy-efficient computation. In this work, we propose a novel insight into integrating SNNs with Graph Transformers and design a Spiking Graph Attention (SGA) module. The matrix multiplication is replaced by sparse addition and mask operations. The linear complexity enables all-pair node interactions on large-scale graphs with limited GPU memory. To our knowledge, our work is the first attempt to introduce SNNs into Graph Transformers. Furthermore, we design SpikeGraphormer, a Dual-branch architecture, combining a sparse GNN branch with our SGA-driven Graph Transformer branch, which can simultaneously perform all-pair node interactions and capture local neighborhoods. SpikeGraphormer consistently outperforms existing state-of-the-art approaches across various datasets and makes substantial improvements in training time, inference time, and GPU memory cost (10 ~ 20x lower than vanilla self-attention). It also performs well in cross-domain applications (image and text classification). We release our code at https://github.com/PHD-lanyu/SpikeGraphormer.

cs.NE↗

arXiv2023

Dynamic Link Prediction Using Graph Representation Learning with Enhanced Structure and Temporal Information

The links in many real networks are evolving with time. The task of dynamic link prediction is to use past connection histories to infer links of the network at a future time. How to effectively learn the temporal and structural pattern of the network dynamics is the key. In this paper, we propose a graph representation learning model based on enhanced structure and temporal information (GRL\_EnSAT). For structural information, we exploit a combination of a graph attention network (GAT) and a self-attention network to capture structural neighborhood. For temporal dynamics, we use a masked self-attention network to capture the dynamics in the link evolution. In this way, GRL\_EnSAT not only learns low-dimensional embedding vectors but also preserves the nonlinear dynamic feature of the evolving network. GRL\_EnSAT is evaluated on four real datasets, in which GRL\_EnSAT outperforms most advanced baselines. Benefiting from the dynamic self-attention mechanism, GRL\_EnSAT yields better performance than approaches based on recursive graph evolution modeling.

cs.SI↗

arXiv2022

Significant Ties Graph Neural Networks for Continuous-Time Temporal Networks Modeling

Temporal networks are suitable for modeling complex evolving systems. It has a wide range of applications, such as social network analysis, recommender systems, and epidemiology. Recently, modeling such dynamic systems has drawn great attention in many domains. However, most existing approaches resort to taking discrete snapshots of the temporal networks and modeling all events with equal importance. This paper proposes Significant Ties Graph Neural Networks (STGNN), a novel framework that captures and describes significant ties. To better model the diversity of interactions, STGNN introduces a novel aggregation mechanism to organize the most significant historical neighbors' information and adaptively obtain the significance of node pairs. Experimental results on four real networks demonstrate the effectiveness of the proposed framework.

cs.SI↗

arXiv2022

Spectrum-BERT: Pre-training of Deep Bidirectional Transformers for Spectral Classification of Chinese Liquors

Spectral detection technology, as a non-invasive method for rapid detection of substances, combined with deep learning algorithms, has been widely used in food detection. However, in real scenarios, acquiring and labeling spectral data is an extremely labor-intensive task, which makes it impossible to provide enough high-quality data for training efficient supervised deep learning models. To better leverage limited samples, we apply pre-training & fine-tuning paradigm to the field of spectral detection for the first time and propose a pre-training method of deep bidirectional transformers for spectral classification of Chinese liquors, abbreviated as Spectrum-BERT. Specifically, first, to retain the model's sensitivity to the characteristic peak position and local information of the spectral curve, we innovatively partition the curve into multiple blocks and obtain the embeddings of different blocks, as the feature input for the next calculation. Second, in the pre-training stage, we elaborately design two pre-training tasks, Next Curve Prediction (NCP) and Masked Curve Model (MCM), so that the model can effectively utilize unlabeled samples to capture the potential knowledge of spectral data, breaking the restrictions of the insufficient labeled samples, and improving the applicability and performance of the model in practical scenarios. Finally, we conduct a large number of experiments on the real liquor spectral dataset. In the comparative experiments, the proposed Spectrum-BERT significantly outperforms the baselines in multiple metrics and this advantage is more significant on the imbalanced dataset. Moreover, in the parameter sensitivity experiment, we also analyze the model performance under different parameter settings, to provide a reference for subsequent research.

cs.LG↗

arXiv2022

Spin-related electronic pathway through single molecule on Au(111)

Spin properties of organic molecules have attracted great interest for their potential applications in spintronic devices and quantum computing. Fe-tetraphenyl porphyrin (FeTPP) is of particular interest for its robust magnetic properties on metallic substrates. FeTPP is prepared in vacuum via on-surface synthesis. Molecular structure and spin-related transport properties are characterized by low-temperature scanning tunneling microscope and spectroscopy at 0.5 K. Density functional theory calculations are performed to understand molecular adsorption and spin distribution on Au(111). The molecular structure of FeTPP is distorted upon adsorption on the substrate. Spin excitations of FeTPP are observed on the Fe atom and high pyrrole groups in differential conductance spectra. The calculated spin density distribution indicates that the electron spin of FeTPP is mainly distributed on the Fe atom. The atomic transmission calculation indicates that electrons transport to substrate is mediated through Fe atom, when the tip is above the high pyrrole group.

cond-mat.mes-hall↗

arXiv2022

SCAI: A Spectral data Classification framework with Adaptive Inference for the IoT platform

Currently, it is a hot research topic to realize accurate, efficient, and real-time identification of massive spectral data with the help of deep learning and IoT technology. Deep neural networks played a key role in spectral analysis. However, the inference of deeper models is performed in a static manner, and cannot be adjusted according to the device. Not all samples need to allocate all computation to reach confident prediction, which hinders maximizing the overall performance. To address the above issues, we propose a Spectral data Classification framework with Adaptive Inference. Specifically, to allocate different computations for different samples while better exploiting the collaboration among different devices, we leverage Early-exit architecture, place intermediate classifiers at different depths of the architecture, and the model outputs the results when the prediction confidence reaches a preset threshold. We propose a training paradigm of self-distillation learning, the deepest classifier performs soft supervision on the shallow ones to maximize their performance and training speed. At the same time, to mitigate the vulnerability of performance to the location and number settings of intermediate classifiers in the Early-exit paradigm, we propose a Position-Adaptive residual network. It can adjust the number of layers in each block at different curve positions, so it can focus on important positions of the curve (e.g.: Raman peak), and accurately allocate the appropriate computational budget based on task performance and computing resources. To the best of our knowledge, this paper is the first attempt to conduct optimization by adaptive inference for spectral detection under the IoT platform. We conducted many experiments, the experimental results show that our proposed method can achieve higher performance with less computational budget than existing methods.

cs.LG↗

arXiv2022

CasSeqGCN: Combining Network Structure and Temporal Sequence to Predict Information Cascades

One important task in the study of information cascade is to predict the future recipients of a message given its past spreading trajectory. While the network structure serves as the backbone of the spreading, an accurate prediction can hardly be made without the knowledge of the dynamics on the network. The temporal information in the spreading sequence captures many hidden features, but predictions based on sequence alone have their limitations. Recent efforts start to explore the possibility of combining both the network structure and the temporal feature. Here, we propose a new end-to-end prediction method CasSeqGCN in which the structure and temporal feature are simultaneously taken into account. A cascade is divided into multiple snapshots which record the network topology and the state of nodes. The graph convolutional network (GCN) is used to learn the representation of a snapshot. A novel aggregation method based on dynamic routing is proposed to aggregate node representation and the long short-term memory (LSTM) model is used to extract temporal information. CasSeqGCN predicts the future cascade size more accurately compared with other state-of-art baseline methods. The ablation study demonstrates that the improvement mainly comes from the design of the input and the GCN layer. We explicitly design an experiment to show the quality of the cascade representation learned by our approach is better than other methods. Our work proposes a new approach to combine the structural and temporal features, which not only gives a useful baseline model for future studies of cascade prediction, but also brings new insights on a wide collection of problems related with dynamics on and of the network.

cs.SI↗