Author name cluster

Song Wang

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.

45 papers

2 author rows

TMLR Journal 2026 Journal Article

Explainable Graph Learning for Particle Accelerator Operations

Song Wang
Chris Tennant
Jundong Li

Particle accelerators are vital tools in physics, medicine, and industry, requiring precise tuning to ensure optimal beam performance. However, real-world deviations from idealized simulations make beam tuning a time-consuming and error-prone process. In this work, we propose an explanation-driven framework for providing actionable insight into beamline operations, with a focus on the injector beamline at the Continuous Electron Beam Accelerator Facility (CEBAF). We represent beamline configurations as heterogeneous graphs, where setting nodes represent elements that human operators can actively adjust during beam tuning, and reading nodes passively provide diagnostic feedback. To identify the most influential setting nodes responsible for differences between any two beamline configurations, our approach first predicts the resulting changes in reading nodes caused by variations in settings, and then learns importance scores that capture the joint influence of multiple setting nodes. Experimental results on real-world CEBAF injector data demonstrate the framework’s ability to generate interpretable insights that can assist human operators in beamline tuning and reduce operational overhead.

AAAI Conference 2026 Conference Paper

GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving

Chunyong Hu
Qi Luo
Jianyun Xu
Song Wang
Qiang Li
Sheng Yang

In the realm of autonomous driving, accurately detecting surrounding obstacles is crucial for effective decision-making. Traditional methods primarily rely on 3D bounding boxes to represent these obstacles, which often fail to capture the complexity of irregularly shaped, real-world objects. To overcome these limitations, we present GUIDE, a novel framework that utilizes 3D Gaussians for instance detection and occupancy prediction. Unlike conventional occupancy prediction methods, GUIDE also offers robust tracking capabilities. Our framework employs a sparse representation strategy, using Gaussian-to-Voxel Splatting to provide fine-grained, instance-level occupancy data without the computational demands associated with dense voxel grids. Experimental validation on the nuScenes dataset demonstrates GUIDE's performance, with an instance occupancy mAP of 21.61, marking a 50% improvement over existing methods, alongside competitive tracking capabilities. GUIDE establishes a new benchmark in autonomous perception systems, effectively combining precision with computational efficiency to better address the complexities of real-world driving environments.

PDF Details DOI

YNIMG Journal 2026 Journal Article

Neurostructural correlates of intolerance of uncertainty: Regional and network-level associations with general psychological distress

Xueling Suo
Li Chen
Graham J Kemp
Song Wang

Intolerance of uncertainty (IU), which is characterized by an inability to endure aversive responses to uncertainty, is a transdiagnostic and transituational risk factor for general psychological distress (GPD). However, its neuroanatomical basis remains unclear. This study investigated the associations between IU and brain structure at both regional and network levels in 115 healthy university students, and explored whether IU mediates the brain-GPD association. Voxel-based morphometry revealed a positive correlation between IU and gray matter volume (GMV) in the right orbitofrontal cortex (OFC). Graph-based analysis of structural covariance networks showed that IU was positively associated with patterns of nodal local efficiency (reflecting local information processing capability) and nodal clustering coefficient (reflecting regional modular connectivity). The brain regions contributing to these network patterns were primarily located within the limbic network (LN) and default mode network (DMN), including the inferior frontal gyrus, middle temporal gyrus, and parahippocampal gyrus. Critically, mediation analyses demonstrated that IU significantly accounting for variance in the link of right OFC GMV and the two structural covariance network patterns with GPD. All findings remained robust after controlling for family socioeconomic status or general anxiety. These results reveal multilevel neuroanatomical features associated with IU, implicating the right OFC and structural covariance patterns of LN and DMN. They further highlight IU as a critical psychological mechanism linking these brain structural features to GPD, offering potential targets for neurobehavioral interventions.

NeurIPS Conference 2025 Conference Paper

$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

Huaizhi Qu
Inyoung Choi
Zhen Tan
Song Wang
Sukwon Yun
Qi Long
Faizan Siddiqui
Kwonjoon Lee

LLM ensembles are widely used for LLM judges. However, how to estimate their accuracy, especially in an efficient way, is unknown. In this paper, we present a principled $\textit{maximum a posteriori}$ (MAP) framework for an economical and precise estimation of the performance of LLM ensemble judgment. We first propose a mixture of Beta-Binomial distributions to model the judgment distribution, revising from the vanilla Binomial distribution. Next, we introduce a conformal prediction-driven approach that enables adaptive stopping during iterative sampling to balance accuracy with efficiency. Furthermore, we design a prior transfer mechanism that utilizes learned distributions on open-source datasets to improve estimation on a target dataset when only scarce annotations are available. Finally, we present $\texttt{BetaConform}$, a framework that integrates our distribution assumption, adaptive stopping, and the prior transfer mechanism to deliver a theoretically guaranteed distribution estimation of LLM ensemble judgment with minimum labeled samples. $\texttt{BetaConform}$ is also validated empirically. For instance, with only $10$ samples from the TruthfulQA dataset, for a Llama ensembled judge, $\texttt{BetaConform}$ gauges its performance with an error margin as small as $3. 37\\%$.

AAAI Conference 2025 Conference Paper

Bias Unveiled: Investigating Social Bias in LLM-Generated Code

Lin Ling
Fazle Rabbi
Song Wang
Jinqiu Yang

Large language models (LLMs) have significantly advanced the field of automated code generation. However, a notable research gap exists in evaluating social biases that may be present in the code produced by LLMs. To solve this issue, we propose a novel fairness framework, i.e., Solar, to assess and mitigate the social biases of LLM-generated code. Specifically, Solar can automatically generate test cases for quantitatively uncovering social biases of the auto-generated code by LLMs. To quantify the severity of social biases in generated code, we develop a dataset that covers a diverse set of social problems. We applied Solar and the crafted dataset to four state-of-the-art LLMs for code generation. Our evaluation reveals severe bias in the LLM-generated code from all the subject LLMs. Furthermore, we explore several prompting strategies for mitigating bias, including Chain-of-Thought (CoT) prompting, combining positive role-playing with CoT prompting and dialogue with Solar. Our experiments show that dialogue with Solar can effectively reduce social bias in LLM-generated code by up to 90%. Last, we make the code and data publicly available is highly extensible to evaluate new social problems.

PDF Details DOI

AAAI Conference 2025 Conference Paper

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

Song Wang
Zhenyu Lei
Zhen Tan
Jiaqi Ding
Xinyu Zhao
Yushun Dong
Guorong Wu
Tianlong Chen

Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain pathways, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework BrainMAP to learn multiple pathways in brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

DIIN: Diffusion Iterative Implicit Networks for Arbitrary-scale Super-resolution

Tao Dai
Song Wang
Hang Guo
Jianping Wang
Zexuan Zhu

Implicit neural representation (INR) aims to represent continuous domain signals via implicit neural functions and has achieved great success in arbitrary-scale image super-resolution (SR). However, most existing INR-based SR methods focus on learning implicit features from independent coordinate, while neglecting interactions of neighborhood coordinates, thus resulting in limited contextual awareness. In this paper, we rethink the forward process of implicit neural functions as a signal diffusion process, we propose a novel Diffusion Iterative Implicit Network (DIIN) for arbitrary-scale SR to promote global signal flow with neighborhood interactions. The DIIN framework mainly consists of stacked Diffusion Iteration Layers with dictionary cross-attention block to enrich the iterative update process with supplementary information. Besides, we develop the Position-Aware Embedding Block to strengthen spatial dependencies between consecutive input samples. Extensive experiments on public datasets demonstrate that our method achieves state-of-the-art or competitive performance, highlighting its effectiveness and efficiency for arbitrary-scale SR. Our code is available at https: //github. com/Song-1205/DIIN.

PDF Details DOI

YNIMG Journal 2025 Journal Article

Disrupted structural connectivity-gray matter covariance coupling and associated cytoarchitectural and transcriptomic profiles in attention-deficit/hyperactivity disorder

Yajing Long
Nanfang Pan
Song Wang
Kun Qin
Qiuxing Chen
Clara S. Vetter
Manpreet K. Singh
Alex Fornito

BACKGROUND: Attention-deficit/hyperactivity disorder (ADHD) has been associated with disrupted axonal connectivity (termed structural connectivity, SC) and altered interregional coupling of gray matter morphometry (termed gray matter covariance, GMC). However, the relationship between SC and GMC in ADHD remains understudied. METHODS: We investigated this relationship by quantifying the coupling between SC and GMC using neuroimaging data from 109 children with ADHD (aged 10.8 ± 2.3) and 105 typically developing controls (aged 11.2 ± 2.4) comparable for age and sex. Publicly accessible cytoarchitectural and transcriptomic datasets were employed to characterize the cellular and molecular correlates of ADHD-related SC-GMC coupling differences, and a machine learning pipeline was used to investigate its potential in classifying children with ADHD. RESULTS: Children with ADHD showed aberrant SC-GMC coupling patterns in the right putamen, left hippocampus, and ventral attention network compared to controls. Their abnormal SC-GMC coupling patterns were correlated with sensory-fugal gradient of cytohistological variation and spatially associated with gene expression enriched for neurodevelopment-related biological pathways, including neuron projection development. The classification model based on SC-GMC couplings achieved an area under the receiver operating characteristic curve (AUC) value of 0.67. CONCLUSIONS: Our findings provide novel insights into atypical couplings between brain gray and white matter structural connectomes in ADHD, their histological and transcriptional correlates, and prospects of using these data to expand clinical phenotyping.

EAAI Journal 2025 Journal Article

Enhancing online industrial quality index prediction with a general deep temporal feature extraction and incremental ensemble modeling framework

Yuchen Zhao
Rui Yang
Jie Ying
Song Wang
Zhenyu Zeng

Data-driven modeling methods for industrial quality index prediction often face the challenge of limited data representation. Using process variable snapshots from a single time step is insufficient for building high-performance soft sensors. Moreover, during online prediction, the performance of soft sensors is affected by diverse operating conditions and concept drift in industrial data streams, leading to performance degradation. To address these challenges, this paper proposes a Temporal Feature Extraction and Incremental Variational Bayesian Regression Ensemble (TFE-IVBRE) framework, which provides a general solution for various online industrial quality index prediction tasks. The TFE-IVBRE framework combines the temporal feature extraction capabilities of deep neural networks, the ability of ensemble learning to handle diverse operating conditions, and the online learning features of variational Bayesian models. An incremental update strategy is also incorporated to maintain consistent prediction performance. Experiments in the Debutanizer Column and Sulfur Recovery Unit scenarios show that the prediction performance of TFE-IVBRE significantly outperforms other static and online comparison models, with the effectiveness of its components validated through ablation studies. Finally, the overall model also demonstrates good robustness. These results offer valuable insights for the advancement of industrial soft sensor development.

TMLR Journal 2025 Journal Article

Generative Risk Minimization for Out-of-Distribution Generalization on Graphs

Song Wang
Zhen Tan
Yaochen Zhu
Chuxu Zhang
Jundong Li

Out-of-distribution (OOD) generalization on graphs aims at dealing with scenarios where the test graph distribution differs from the training graph distributions. Compared to i.i.d. data like images, the OOD generalization problem on graph-structured data remains challenging due to the non-i.i.d. property and complex structural information on graphs. Recently, several works on graph OOD generalization have explored extracting invariant subgraphs that share crucial classification information across different distributions. Nevertheless, such a strategy could be suboptimal for entirely capturing the invariant information, as the extraction of discrete structures could potentially lead to the loss of invariant information or the involvement of spurious information. In this paper, we propose an innovative framework, named Generative Risk Minimization (GRM), designed to generate an invariant subgraph for each input graph to be classified, instead of extraction. To address the challenge of optimization in the absence of optimal invariant subgraphs (i.e., ground truths), we derive a tractable form of the proposed GRM objective by introducing a latent causal variable, and its effectiveness is validated by our theoretical analysis. We further conduct extensive experiments across a variety of real-world graph datasets for both node-level and graph-level OOD generalization, and the results demonstrate the superiority of our framework GRM.

NeurIPS Conference 2025 Conference Paper

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

Yinhan He
Wendy Zheng
Song Wang
Zaiyi Zheng
Yushun Dong
Yaochen Zhu
Jundong Li

In-Context Learning (ICL) is a technique where large language models (LLMs) leverage multiple demonstrations (i. e. , examples) to perform tasks. With the recent expansion of LLM context windows, many-shot ICL (generally with more than 50 demonstrations) can lead to significant performance improvements on a variety of language tasks such as text classification and question answering. Nevertheless, ICL faces the issue of demonstration order instability (ICL-DOI), which means that performance varies significantly depending on the order of demonstrations. Moreover, ICL-DOI persists in many-shot ICL, validated by our thorough experimental investigation. Current strategies for handling ICL-DOI are not applicable to many-shot ICL due to two critical challenges: (1) Most existing methods assess demonstration order quality by first prompting the LLM, then using heuristic metrics based on the LLM's predictions. In the many-shot scenarios, these metrics without theoretical grounding become unreliable, where the LLMs struggle to effectively utilize information from long input contexts, making order distinctions less clear. The requirement to examine all orders for the large number of demonstrations is computationally infeasible due to the super-exponential complexity of the order space in many-shot ICL. To tackle the first challenge, we design a demonstration order evaluation metric based on information theory for measuring order quality, which effectively quantifies the usable information gain of a given demonstration order. To address the second challenge, we propose a hierarchical demonstration order optimization method named \texttt{HIDO} that enables a more refined exploration of the order space, achieving high ICL performance without the need to evaluate all possible orders. Extensive experiments on multiple LLMs and real-world datasets demonstrate that our \texttt{HIDO} method consistently and efficiently outperforms other baselines. Our code project can be found at https: //github. com/YinhanHe123/HIDO/.

ICLR Conference 2025 Conference Paper

Integrative Decoding: Improving Factuality via Implicit Self-consistency

Yi Cheng
Xiao Liang
Yeyun Gong
Wen Xiao
Song Wang
Yuji Zhang 0002
Wenjun Hou
Kaishuai Xu

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models. Nonetheless, existing methods usually have strict constraints on the task format, largely limiting their applicability. In this paper, we present Integrative Decoding (ID), to unlock the potential of self-consistency in open-ended generation tasks. ID operates by constructing a set of inputs, each prepended with a previously sampled response, and then processes them concurrently, with the next token being selected by aggregating of all their corresponding predictions at each decoding step. In essence, this simple approach implicitly incorporates self-consistency in the decoding objective. Extensive evaluation shows that ID consistently enhances factuality over a wide range of language models, with substantial improvements on the TruthfulQA (+11.2%), Biographies (+15.4%) and LongFact (+8.5%) benchmarks. The performance gains amplify progressively as the number of sampled responses increases, indicating the potential of ID to scale up with repeated sampling.

IJCAI Conference 2025 Conference Paper

Interpreting Pretrained Language Models via Concept Bottlenecks (Extended Abstract)

Zhen Tan
Lu Cheng
Song Wang
Yuan Bo
Jundong Li
Huan Liu

Pretrained language models (PLMs) achieve state-of-the-art results but often function as ``black boxes'', hindering interpretability and responsible deployment. While methods like attention analysis exist, they often lack clarity and intuitiveness. We propose interpreting PLMs through high-level, human-understandable concepts using Concept Bottleneck Models (CBMs). This extended abstract introduces C3M (ChatGPT-guided Concept augmentation with Concept-level Mixup), a novel framework for training Concept-Bottleneck-Enabled PLMs (CBE-PLMs). C3M leverages Large Language Models (LLMs) like ChatGPT to augment concept sets and generate noisy concept labels, combined with a concept-level MixUp mechanism to enhance robustness and effectively learn from both human-annotated and machine-generated concepts. Empirical results show our approach provides intuitive explanations, aids model diagnosis via test-time intervention, and improves the interpretability-utility trade-off, even with limited or noisy concept annotations. This is an concise version of [Tan et al. , 2024b], recipient of the Best Paper Award at PAKDD 2024. Code and data are released at https: //github. com/Zhen-Tan-dmml/CBM_NLP. git.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

Tianyu Hu
Zhen Tan
Song Wang
Huaizhi Qu
Tianlong Chen

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic aggregation methods (e. g. , majority voting), which can fail even when individual agents provide correct answers. To address this, we propose a multi-agent debate judge framework where agents collaboratively reason and iteratively refine their responses. We formalize the debate process mathematically, analyzing agent interactions and proving that debate amplifies correctness compared to static ensembles. To enhance efficiency, we introduce a stability detection mechanism that models judge consensus dynamics via a time-varying Beta-Binomial mixture, with adaptive stopping based on distributional similarity (Kolmogorov-Smirnov test). This mechanism models the judges' collective correct rate dynamics using a time-varying mixture of Beta-Binomial distributions and employs an adaptive stopping criterion based on distributional similarity (Kolmogorov-Smirnov statistic). Experiments across multiple benchmarks and models demonstrate that our framework improves judgment accuracy over majority voting while maintaining computational efficiency.

IJCAI Conference 2025 Conference Paper

Reliable and Calibrated Semantic Occupancy Prediction by Hybrid Uncertainty Learning

Song Wang
Zhongdao Wang
Jiawei Yu
Wentong Li
Bailan Feng
Junbo Chen
Jianke Zhu

Vision-centric semantic occupancy prediction plays a crucial role in autonomous driving, which requires accurate and reliable predictions from low-cost sensors. Although having notably narrowed the accuracy gap with LiDAR, there is still few research effort to explore the reliability and calibration in predicting semantic occupancy from camera. In this paper, we conduct a comprehensive evaluation of existing semantic occupancy prediction models from a reliability perspective for the first time. Despite the gradual alignment of camera-based models with LiDAR in terms of accuracy, a significant reliability gap still persists. To address this concern, we propose ReliOcc, a method designed to enhance the reliability of camera-based occupancy networks. ReliOcc provides a plug-and-play scheme for existing models, which integrates hybrid uncertainty from individual voxels with sampling-based noise and relative voxels through mix-up learning. Besides, an uncertainty-aware calibration strategy is devised to further improve model reliability in offline mode. Extensive experiments under various settings demonstrate that ReliOcc significantly enhances the reliability of learned model while maintaining the accuracy for both geometric and semantic predictions. Notably, our proposed approach exhibits robustness to sensor failures and out of domain noises during inference.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective

Yiming Xu
Zhen Peng
Bin Shi
Xu Hua
Bo Dong
Song Wang
Chen Chen

The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies.

PDF Details DOI

ICRA Conference 2025 Conference Paper

Self-Supervised Learning of Reconstructing Deformable Linear Objects Under Single-Frame Occluded View

Song Wang
Guanghui Shen
Shirui Wu
Dan Wu 0008

Deformable linear objects (DLOs), such as ropes, cables, and rods, are common in various scenarios, and accurate occlusion reconstruction of them is crucial for effective robotic manipulation. Previous studies for DLO reconstruction either rely on supervised learning, which is limited by the availability of labeled real-world data, or geometric approaches, which fail to capture global features and often struggle with occlusions and complex shapes. This paper presents a novel DLO occlusion reconstruction framework that integrates self-supervised point cloud completion with traditional techniques like clustering, sorting, and fitting to generate ordered key points. A memory module is proposed to enhance the self-supervised training process by consolidating prototype information, while DLO shape constraints are utilized to improve reconstruction accuracy. Experimental results on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art algorithms, particularly in scenarios involving complex occlusions and intricate self-intersections.

AAAI Conference 2025 Conference Paper

Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach

Zhen Tan
Jie Peng
Song Wang
Lijie Hu
Tianlong Chen
Huan Liu

Large Language Models (LLMs) have brought significant advances across various NLP tasks through few-shot or zero-shot prompting, bypassing the need for parameter tuning. However, the "black-box" nature behind their massive parameter sizes increases the "hallucination" concerns, especially in high-stakes applications (e.g., healthcare), where decision mistakes can lead to severe consequences. In contrast, human decision-making relies on complex cognitive processes, such as the ability to sense and adaptively correct mistakes through conceptual understanding. Drawing inspiration from human cognition, we propose an innovative metacognitive approach CLEAR, to equip LLMs with capabilities for self-aware error identification and correction. Our framework constructs concept-specific sparse subnetworks that indicate decision processes. This provides a novel interface for model {intervention} after deployment. The benefits include: (i) at inference time, our metacognitive LLMs can self-consciously identify potential mispredictions with minimum human involvement, (ii) the model can self-correct its errors efficiently without additional tuning, and (iii) the correction procedure is not only self-explanatory but also user-friendly, enhancing model interpretability and accessibility. With these metacognitive features, our approach pioneers a new path toward the trustworthiness of LLMs.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning

Xingbo Fu
Zihan Chen
Yinhan He
Song Wang
Binchi Zhang
Chen Chen
Jundong Li

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such as graph property prediction. In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes. In particular, graph properties are usually associated with invariant label-relevant substructures (i.e., subgraphs) across clients, while label-irrelevant substructures can appear in a client-specific manner. The issue of distribution shifts of graph data hinders the efficiency of GNN training and leads to serious performance degradation in FGL. To tackle the aforementioned issue, we propose a novel FGL framework entitled FedVN that eliminates distribution shifts through client-specific graph augmentation strategies with multiple learnable Virtual Nodes (VNs). Specifically, FedVN lets the clients jointly learn a set of shared VNs while training a global GNN model. To eliminate distribution shifts, each client trains a personalized edge generator that determines how the VNs connect local graphs in a client-specific manner. Furthermore, we provide theoretical analyses indicating that FedVN can eliminate distribution shifts of graph data across clients. Comprehensive experiments on four datasets under five settings demonstrate the superiority of our proposed FedVN over nine baselines.

PDF Details DOI

TMLR Journal 2024 Journal Article

Federated Graph Learning with Graphless Clients

Xingbo Fu
Song Wang
Yushun Dong
Binchi Zhang
Chen Chen
Jundong Li

Federated graph learning is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated learning systems where only a part of the clients have such data while other clients graphless clients may only have features. This naturally leads to a novel problem in federated graph learning: how to jointly train a model over distributed graph data with graphless clients? To tackle this problem, we propose a novel Federated Graph Structure Learning (FedGSL) framework in this paper. In FedGSL, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments on five real-world graph datasets demonstrate the superiority of FedGSL over other five federated learning approaches.

IJCAI Conference 2024 Conference Paper

Label-efficient Semantic Scene Completion with Scribble Annotations

Song Wang
Jiawei Yu
Wentong Li
Hao Shi
Kailun Yang
Junbo Chen
Jianke Zhu

Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or benchmark in a fully supervised manner. While the dense occupancy grids need point-wise semantic annotations, which incur expensive and tedious labeling costs. In this paper, we build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. In particular, we propose a simple yet effective approach called Scribble2Scene, which bridges the gap between the sparse scribble annotations and fully-supervision. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance. Experiments on SemanticKITTI demonstrate that Scribble2Scene achieves competitive performance against the fully-supervised counterparts, showing 99% performance of the fully-supervised models with only 13. 5% voxels labeled. Both annotations of ScribbleSC and our full implementation are available at https: //github. com/songw-zju/Scribble2Scene.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Mixture of Demonstrations for In-Context Learning

Song Wang
Zihan Chen
Chengshuai Shi
Cong Shen
Jundong Li

In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle various tasks by providing input-output examples as additional inputs, referred to as demonstrations. Nevertheless, the performance of ICL could be easily impacted by the quality of selected demonstrations. Existing efforts generally learn a retriever model to score each demonstration for selecting suitable demonstrations, however, the effect is suboptimal due to the large search space and the noise from unhelpful demonstrations. In this study, we introduce MoD, which partitions the demonstration pool into groups, each governed by an expert to reduce search space. We further design an expert-wise training strategy to alleviate the impact of unhelpful demonstrations when optimizing the retriever model. During inference, experts collaboratively retrieve demonstrations for the input query to enhance the ICL performance. We validate MoD via experiments across a range of NLP datasets and tasks, demonstrating its state-of-the-art performance and shedding new light on the future design of retrieval methods for ICL.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Orthogonal Dictionary Guided Shape Completion Network for Point Cloud

Pingping Cai
Deja Scott
Xiaoguang Li
Song Wang

Point cloud shape completion, which aims to reconstruct the missing regions of the incomplete point clouds with plausible shapes, is an ill-posed and challenging task that benefits many downstream 3D applications. Prior approaches achieve this goal by employing a two-stage completion framework, generating a coarse yet complete seed point cloud through an encoder-decoder network, followed by refinement and upsampling. However, the encoded features suffer from information loss of the missing portion, leading to an inability of the decoder to reconstruct seed points with detailed geometric clues. To tackle this issue, we propose a novel Orthogonal Dictionary Guided Shape Completion Network (ODGNet). The proposed ODGNet consists of a Seed Generation U-Net, which leverages multi-level feature extraction and concatenation to significantly enhance the representation capability of seed points, and Orthogonal Dictionaries that can learn shape priors from training samples and thus compensate for the information loss of the missing portions during inference. Our design is simple but to the point, extensive experiment results indicate that the proposed method can reconstruct point clouds with more details and outperform previous state-of-the-art counterparts. The implementation code is available at https://github.com/corecai163/ODGNet.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network

Canyu Zhang
Zhenyao Wu
Xinyi Wu
Ziyu Zhao
Song Wang

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic segmentation methods usually require large-scale annotated point clouds for training and cannot handle new categories. While a few-shot learning method was proposed recently to address these two problems, it suffers from high computational complexity caused by graph construction and inability to learn fine-grained relationships among points due to the use of pooling operations. In this paper, we further address these problems by developing a new multi-layer transformer network for few-shot point cloud semantic segmentation. In the proposed network, the query point cloud features are aggregated based on the class-specific support features in different scales. Without using pooling operations, our method makes full use of all pixel-level features from the support samples. By better leveraging the support features for few-shot learning, the proposed method achieves the new state-of-the-art performance, with 15% less inference time, over existing few-shot 3D point cloud segmentation models on the S3DIS dataset and the ScanNet dataset. Our code is available at https://github.com/czzhang179/SCAT.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution

Yushun Dong
Song Wang
Jing Ma
Ninghao Liu
Jundong Li

Graph Neural Networks (GNNs) have emerged as the leading paradigm for solving graph analytical problems in various real-world applications. Nevertheless, GNNs could potentially render biased predictions towards certain demographic subgroups. Understanding how the bias in predictions arises is critical, as it guides the design of GNN debiasing mechanisms. However, most existing works overwhelmingly focus on GNN debiasing, but fall short on explaining how such bias is induced. In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes. Specifically, we propose a novel strategy named Probabilistic Distribution Disparity (PDD) to measure the bias exhibited in GNNs, and develop an algorithm to efficiently estimate the influence of each training node on such bias. We verify the validity of PDD and the effectiveness of influence estimation through experiments on real-world datasets. Finally, we also demonstrate how the proposed framework could be used for debiasing GNNs. Open-source code can be found at https://github.com/yushundong/BIND.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Label-efficient Segmentation via Affinity Propagation

Wentong Li
Yuqian Yuan
Song Wang
Wenyu Liu
Dongqi Tang
Jian Liu
Jianke Zhu
Lei Zhang

Weakly-supervised segmentation with label-efficient sparse annotations has attracted increasing research attention to reduce the cost of laborious pixel-wise labeling process, while the pairwise affinity modeling techniques play an essential role in this task. Most of the existing approaches focus on using the local appearance kernel to model the neighboring pairwise potentials. However, such a local operation fails to capture the long-range dependencies and ignores the topology of objects. In this work, we formulate the affinity modeling as an affinity propagation process, and propose a local and a global pairwise affinity terms to generate accurate soft pseudo labels. An efficient algorithm is also developed to reduce significantly the computational cost. The proposed approach can be conveniently plugged into existing segmentation networks. Experiments on three typical label-efficient segmentation tasks, i. e. box-supervised instance segmentation, point/scribble-supervised semantic segmentation and CLIP-guided semantic segmentation, demonstrate the superior performance of the proposed approach.

AAAI Conference 2023 Conference Paper

Parametric Surface Constrained Upsampler Network for Point Cloud

Pingping Cai
Zhenyao Wu
Xinyi Wu
Song Wang

Designing a point cloud upsampler, which aims to generate a clean and dense point cloud given a sparse point representation, is a fundamental and challenging problem in computer vision. A line of attempts achieves this goal by establishing a point-to-point mapping function via deep neural networks. However, these approaches are prone to produce outlier points due to the lack of explicit surface-level constraints. To solve this problem, we introduce a novel surface regularizer into the upsampler network by forcing the neural network to learn the underlying parametric surface represented by bicubic functions and rotation functions, where the new generated points are then constrained on the underlying surface. These designs are integrated into two different networks for two tasks that take advantages of upsampling layers -- point cloud upsampling and point cloud completion for evaluation. The state-of-the-art experimental results on both tasks demonstrate the effectiveness of the proposed method. The implementation code will be available at https://github.com/corecai163/PSCU.

PDF Details DOI

YNIMG Journal 2022 Journal Article

COVID‐19 vicarious traumatization links functional connectome to general distress

Xueling Suo
Chao Zuo
Huan Lan
Nanfang Pan
Xun Zhang
Graham J. Kemp
Song Wang
Qiyong Gong

As characterized by repeated exposure of others’ trauma, vicarious traumatization is a common negative psychological reaction during the COVID-19 pandemic and plays a crucial role in the development of general mental distress. This study aims to identify functional connectome that encodes individual variations of pandemic-related vicarious traumatization and reveal the underlying brain-vicarious traumatization mechanism in predicting general distress. The eligible subjects were 105 general university students (60 females, aged from 19 to 27 years) undergoing brain MRI scanning and baseline behavioral tests (October 2019 to January 2020), whom were re-contacted for COVID-related vicarious traumatization measurement (February to April 2020) and follow-up general distress evaluation (March to April 2021). We applied a connectome-based predictive modeling (CPM) approach to identify the functional connectome supporting vicarious traumatization based on a 268-region-parcellation assigned to network memberships. The CPM analyses showed that only the negative network model stably predicted individuals’ vicarious traumatization scores (q2 = -0. 18, MSE = 617, r [predicted, actual] = 0. 18, p = 0. 024), with the contributing functional connectivity primarily distributed in the fronto-parietal, default mode, medial frontal, salience, and motor network. Furthermore, mediation analysis revealed that vicarious traumatization mediated the influence of brain functional connectome on general distress. Importantly, our results were independent of baseline family socioeconomic status, other stressful life events and general mental health as well as age, sex and head motion. Our study is the first to provide evidence for the functional neural markers of vicarious traumatization and reveal an underlying neuropsychological pathway to predict distress symptoms in which brain functional connectome affects general distress via vicarious traumatization.

IJCAI Conference 2022 Conference Paper

FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs

Song Wang
Yushun Dong
Xiao Huang
Chen Chen
Jundong Li

Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class. To tackle the bottleneck of label scarcity, recent works propose to incorporate few-shot learning frameworks for fast adaptations to graph classes with limited labeled graphs. Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set. However, existing methods generally ignore task correlations among meta-training tasks while treating them independently. Nevertheless, such task correlations can advance the model generalization to the target task for better classification performance. On the other hand, it remains non-trivial to utilize task correlations due to the complex components in a large number of meta-training tasks. To deal with this, we propose a novel few-shot learning framework FAITH that captures task correlations via constructing a hierarchical task graph at different granularities. Then we further design a loss-based sampling strategy to select tasks with more correlated classes. Moreover, a task-specific classifier is proposed to utilize the learned task correlations for few-shot classification. Extensive experiments on four prevalent few-shot graph classification datasets demonstrate the superiority of FAITH over other state-of-the-art baselines.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Graph Few-shot Learning with Task-specific Structures

Song Wang
Chen Chen
Jundong Li

Graph few-shot learning is of great importance among various graph learning tasks. Under the few-shot scenario, models are often required to conduct classification given limited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i. e. , the graph that the meta-task is sampled from) to learn node representations. Consequently, the learned representations for the same nodes are identical in all meta-tasks. Since the class sets are different across meta-tasks, node representations should be task-specific to promote classification performance. Therefore, to adaptively learn node representations across meta-tasks, we propose a novel framework that learns a task-specific structure for each meta-task. To handle the variety of nodes across meta-tasks, we extract relevant nodes and learn task-specific structures based on node influence and mutual information. In this way, we can learn node representations with the task-specific structure tailored for each meta-task. We further conduct extensive experiments on five node classification datasets under both single- and multiple-graph settings to validate the superiority of our framework over the state-of-the-art baselines.

YNIMG Journal 2022 Journal Article

Patterns of a structural covariance network associated with dispositional optimism during late adolescence

Han Lai
Xiangzhen Kong
Yajun Zhao
Nanfang Pan
Xun Zhang
Min He
Song Wang
Qiyong Gong

Dispositional optimism (hereinafter, optimism), as a vital character strength, reflects the tendency to hold generalized positive expectancies for future outcomes. A great number of studies have consistently shown the importance of optimism to a spectrum of physical and mental health outcomes. However, less attention has been given to the intrinsic neurodevelopmental patterns associated with interindividual differences in optimism. Here, we investigated this important question in a large sample comprising 231 healthy adolescents (16-20 years old) via structural magnetic resonance imaging and behavioral tests. We constructed individual structural covariance networks based on cortical gyrification using a recent novel approach combining probability density estimation and Kullback-Leibler divergence and estimated global (global efficiency, local efficiency and small-worldness) and regional (betweenness centrality) properties of these constructed networks using graph theoretical analysis. Partial correlations adjusted for age, sex and estimated total intracranial volume showed that optimism was positively related to global and local efficiency but not small-worldness. Partial least squares correlations indicated that optimism was positively linked to a pronounced betweenness centrality pattern, in which twelve cognition-, emotion-, and motivation-related regions made robust and reliable contributions. These findings remained basically consistent after additionally controlling for family socioeconomic status and showed significant correlations with optimism scores from 2.5 years before, which replicated the main findings. The current work, for the first time, delineated characteristics of the cortical gyrification covariance network associated with optimism, extending previous neurobiological understandings of optimism, which may navigate the development of interventions on a neural network level aimed at raising optimism.

AAAI Conference 2022 Conference Paper

Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation

Xinyi Wu
Zhenyao Wu
Yuhang Lu
Lili Ju
Song Wang

In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during training. In this case, traditional unsupervised domain adaptation models usually fail since they cannot adapt to the target domain with over-fitting to one (or few) target samples. To address this problem, existing OSUDA methods usually integrate a style-transfer module to perform domain randomization based on the unlabeled target sample, with which multiple domains around the target sample can be explored during training. However, such a style-transfer module relies on an additional set of images as style reference for pre-training and also increases the memory demand for domain adaptation. Here we propose a new OSUDA method that can effectively relieve such computational burden. Specifically, we integrate several style-mixing layers into the segmentor which play the role of style-transfer module to stylize the source images without introducing any learned parameters. Moreover, we propose a patchwise prototypical matching (PPM) method to weighted consider the importance of source pixels during the supervised training to relieve the negative adaptation. Experimental results show that our method achieves new state-of-the-art performance on two commonly used benchmarks for domain adaptive semantic segmentation under the one-shot setting and is more efficient than all comparison approaches.

AAAI Conference 2021 Conference Paper

Binaural Audio-Visual Localization

Xinyi Wu
Zhenyao Wu
Lili Ju
Song Wang

Localizing sound sources in a visual scene has many important applications and quite a few traditional or learning-based methods have been proposed for this task. Humans have the ability to roughly localize sound sources within or beyond the range of the vision using their binaural system. However most existing methods use monaural audio, instead of binaural audio, as a modality to help the localization. In addition, prior works usually localize sound sources in the form of object-level bounding boxes in images or videos and evaluate the localization accuracy by examining the overlap between the ground-truth and predicted bounding boxes. This is too rough since a real sound source is often only a part of an object. In this paper, we propose a deep learning method for pixel-level sound source localization by leveraging both binaural recordings and the corresponding videos. Specifically, we design a novel Binaural Audio-Visual Network (BAVNet), which concurrently extracts and integrates features from binaural recordings and videos. We also propose a point-annotation strategy to construct pixel-level ground truth for network training and performance evaluation. Experimental results on Fair-Play and YT-Music datasets demonstrate the effectiveness of the proposed method and show that binaural audio can greatly improve the performance of localizing the sound sources, especially when the quality of the visual information is limited.

AAAI Conference 2021 Conference Paper

Multi-Domain Multi-Task Rehearsal for Lifelong Learning

Fan Lyu
Shuai Wang
Wei Feng
Zihan Ye
Fuyuan Hu
Song Wang

Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i. e. , biased forgetting of previous knowledge when moving to new tasks. However, the old tasks of the most previous rehearsal-based methods suffer from the unpredictable domain shift when training the new task. This is because these methods always ignore two significant factors. First, the Data Imbalance between the new task and old tasks that makes the domain of old tasks prone to shift. Second, the Task Isolation among all tasks will make the domain shift toward unpredictable directions; To address the unpredictable domain shift, in this paper, we propose Multi- Domain Multi-Task (MDMT) rehearsal to train the old tasks and new task parallelly and equally to break the isolation among tasks. Specifically, a two-level angular margin loss is proposed to encourage the intra-class/task compactness and inter-class/task discrepancy, which keeps the model from domain chaos. In addition, to further address domain shift of the old tasks, we propose an optional episodic distillation loss on the memory to anchor the knowledge for each old task. Experiments on benchmark datasets validate the proposed approach can effectively mitigate the unpredictable domain shift.

ICRA Conference 2021 Conference Paper

Robot Motion Control with Compressive Feedback

Congjian Li
Song Wang
Siyu Wang
Sheng Bi
Yisheng Guan
Ning Xi 0001

Robot motion control aims to generate control inputs for a robotic system to track a planned trajectory. Feedback provided by sensors plays an essential role in motion control by improving system performance when external disturbances and/or initial errors exist. However, feedback signals, such as images are often of a large size, which imposes a heavy computational burden on the system. In this paper, a new robot motion control scheme is proposed based on compressive feedback to improve feedback rate. The controller is designed in non-vector space using compressive feedback. As an application, visual servoing is formulated under the proposed framework by considering a feedback image as a set, instead of a traditional feature vector. Experiments are conducted to validate the proposed scheme.

AAAI Conference 2020 Conference Paper

Complementary-View Multiple Human Tracking

Ruize Han
Wei Feng
Jiewen Zhao
Zicheng Niu
Yujun Zhang
Liang Wan
Song Wang

The global trajectories of targets on ground can be well captured from a top view in a high altitude, e. g. , by a dronemounted camera, while their local detailed appearances can be better recorded from horizontal views, e. g. , by a helmet camera worn by a person. This paper studies a new problem of multiple human tracking from a pair of top- and horizontalview videos taken at the same time. Our goal is to track the humans in both views and identify the same person across the two complementary views frame by frame, which is very challenging due to very large ﬁeld of view difference. In this paper, we model the data similarity in each view using appearance and motion reasoning and across views using appearance and spatial reasoning. Combing them, we formulate the proposed multiple human tracking as a joint optimization problem, which can be solved by constrained integer programming. We collect a new dataset consisting of top- and horizontal-view video pairs for performance evaluation and the experimental results show the effectiveness of the proposed method.

AAAI Conference 2020 Conference Paper

Multi-Spectral Salient Object Detection by Adversarial Domain Adaptation

Shaoyue Song
Hongkai Yu
Zhenjiang Miao
Jianwu Fang
Kang Zheng
Cong Ma
Song Wang

Although there are many existing research works about the salient object detection (SOD) in RGB images, there are still many complex situations that regular RGB images cannot provide enough cues for the accurate SOD, such as the shadow effect, similar appearance between background and foreground, strong or insufﬁcient illumination, etc. Because of the success of near-infrared spectrum in many computer vision tasks, we explore the multi-spectral SOD in the synchronized RGB images and near-infrared (NIR) images for the both simple and complex situations. We assume that the RGB SOD in the existing RGB image datasets could provide references for the multi-spectral SOD problem. In this paper, we ﬁrst collect and will publicize a large multi-spectral dataset including 780 synchronized RGB and NIR image pairs for the multi-spectral SOD problem in the simple and complex situations. We model this research problem as an adversarial domain adaptation from the existing RGB image dataset (source domain) to the collected multi-spectral dataset (target domain). Experimental results show the effectiveness and accuracy of the proposed adversarial domain adaptation for the multi-spectral SOD.

AAAI Conference 2020 Conference Paper

Multi-Type Self-Attention Guided Degraded Saliency Detection

Ziqi Zhou
Zheng Wang
Huchuan Lu
Song Wang
Meijun Sun

Existing saliency detection techniques are sensitive to image quality and perform poorly on degraded images. In this paper, we systematically analyze the current status of the research on detecting salient objects from degraded images and then propose a new multi-type self-attention network, namely MSANet, for degraded saliency detection. The main contributions include: 1) Applying attention transfer learning to promote semantic detail perception and internal feature mining of the target network on degraded images; 2) Developing a multi-type self-attention mechanism to achieve the weight recalculation of multi-scale features. By computing global and local attention scores, we obtain the weighted features of different scales, effectively suppress the interference of noise and redundant information, and achieve a more complete boundary extraction. The proposed MSANet converts low-quality inputs to high-quality saliency maps directly in an end-to-end fashion. Experiments on seven widely-used datasets show that our approach produces good performance on both clear and degraded images.

AAAI Conference 2020 Conference Paper

SalSAC: A Video Saliency Prediction Model with Shuffled Attentions and Correlation-Based ConvLSTM

Xinyi Wu
Zhenyao Wu
Jinglin Zhang
Lili Ju
Song Wang

The performance of predicting human ﬁxations in videos has been much enhanced with the help of development of the convolutional neural networks (CNN). In this paper, we propose a novel end-to-end neural network “SalSAC” for video saliency prediction, which uses the CNN-LSTM-Attention as the basic architecture and utilizes the information from both static and dynamic aspects. To better represent the static information of each frame, we ﬁrst extract multi-level features of same size from different layers of the encoder CNN and calculate the corresponding multi-level attentions, then we randomly shufﬂe these attention maps among levels and multiply them to the extracted multi-level features respectively. Through this way, we leverage the attention consistency across different layers to improve the robustness of the network. On the dynamic aspect, we propose a correlationbased ConvLSTM to appropriately balance the inﬂuence of the current and preceding frames to the prediction. Experimental results on the DHF1K, Hollywood2 and UCF-sports datasets show that SalSAC outperforms many existing stateof-the-art methods.

AAAI Conference 2018 Conference Paper

Co-Saliency Detection Within a Single Image

Hongkai Yu
Kang Zheng
Jianwu Fang
Hao Guo
Wei Feng
Song Wang

Recently, saliency detection in a single image and co-saliency detection in multiple images have drawn extensive research interest in the vision community. In this paper, we investigate a new problem of co-saliency detection within a single image, i. e. , detecting within-image co-saliency. By identifying common saliency within an image, e. g. , highlighting multiple occurrences of an object class with similar appearance, this work can beneﬁt many important applications, such as the detection of objects of interest, more robust object recognition, reduction of information redundancy, and animation synthesis. We propose a new bottom-up method to address this problem. Speciﬁcally, a large number of object proposals are ﬁrst detected from the image. Then we develop an optimization algorithm to derive a set of proposal groups, each of which contains multiple proposals showing good common saliency in the original image. For each proposal group, we calculate a co-saliency map and then use a low-rank based algorithm to fuse the maps calculated from all the proposal groups for the ﬁnal co-saliency map in the image. In the experiment, we collect a new dataset of 364 color images with within-image cosaliency. Experiment results show that the proposed method can better detect the within-image co-saliency than existing algorithms.

AAAI Conference 2018 Conference Paper

Cross-View Person Identification by Matching Human Poses Estimated With Confidence on Each Body Joint

Guoqiang Liang
Xuguang Lan
Kang Zheng
Song Wang
Nanning Zheng

Cross-view person identification (CVPI) from multiple temporally synchronized videos taken by multiple wearable cameras from different, varying views is a very challenging but important problem, which has attracted more interests recently. Current state-of-the-art performance of CVPI is achieved by matching appearance and motion features across videos, while the matching of pose features does not work effectively given the high inaccuracy of the 3D human pose estimation on videos/images collected in the wild. In this paper, we introduce a new metric of confidence to the 3D human pose estimation and show that the combination of the inaccurately estimated human pose and the inferred confidence metric can be used to boost the CVPI performance –the estimated pose information can be integrated to the appearance and motion features to achieve the new state-of-the-art CVPI performance. More specifically, the estimated confidence metric is measured at each humanbody joint and the joints with higher confidence are weighted more in the pose matching for CVPI. In the experiments, we validate the proposed method on three wearablecamera video datasets and compare the performance against several other existing CVPI methods.

AAAI Conference 2018 Conference Paper

Curve-Structure Segmentation From Depth Maps: A CNN-Based Approach and Its Application to Exploring Cultural Heritage Objects

Yuhang Lu
Jun Zhou
Jing Wang
Jun Chen
Karen Smith
Colin Wilder
Song Wang

Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map. Different from most classical low-level image segmentation methods that are known to be very sensitive to the noise and occlusions, we propose a new supervised learning algorithm based on Convolutional Neural Network (CNN) to implicitly learn and utilize more curve geometry and pattern information for addressing this challenging problem. More speciﬁcally, we ﬁrst propose a Fully Convolutional Network (FCN) to estimate the skeleton of curve structures and at each skeleton pixel, a scale value is estimated to reﬂect the local curve width. Then we propose a dense prediction network to re- ﬁne the estimated curve skeletons. Based on the estimated scale values, we ﬁnally develop an adaptive thresholding algorithm to achieve the ﬁnal segmentation of curve structures. In the experiment, we validate the performance of the proposed method on a dataset of depth images scanned from unearthed pottery sherds dating to the Woodland period of Southeastern North America.

YNIMG Journal 2017 Journal Article

Hope and the brain: Trait hope mediates the protective role of medial orbitofrontal cortex spontaneous activity against anxiety

Song Wang
Xin Xu
Ming Zhou
Taolin Chen
Xun Yang
Guangxiang Chen
Qiyong Gong

As a central research topic in the field of positive psychology, hope refers to an individual's goal-oriented expectations that include both agency thinking (i. e. , the motivation to initiate and sustain actions to achieve goals) and pathway thinking (i. e. , the capacity to find ways toward goals). Evidence from many previous studies has shown the role of hope in protecting against anxiety. However, little is known about the neurobiological basis of hope and the underlying mechanism that how hope reduces anxiety in the brain. Here, we employed fractional amplitude of low-frequency fluctuations (fALFF) to investigate these issues in 231 high school students using resting-state functional magnetic resonance imaging (RS-fMRI). The whole-brain correlation analyses revealed that higher trait hope was related to lower fALFF in the bilateral medial orbitofrontal cortex (mOFC), which is involved in reward-related processing, motivation production, problem solving and goal-directed behaviors. Furthermore, mediation analyses suggested that trait hope acted as a mediator in the association between mOFC spontaneous activity and anxiety. These results persisted even after adjusting for the effects of positive and negative affect. Overall, this study provides the first evidence for functional brain substrates underlying trait hope and reveals a potential mechanism that trait hope mediates the protective role of spontaneous brain activity against anxiety.

IJCAI Conference 2015 Conference Paper

Simple Atom Selection Strategy for Greedy Matrix Completion

Zebang Shen
Hui Qian
Tengfei Zhou
Song Wang

In this paper we focus on the greedy matrix completion problem. A simple atom selection strategy is proposed to find the optimal atom in each iteration by alternating minimization. Based on this per-iteration strategy, we devise a greedy algorithm and establish an upper bound of the approximating error. To evaluate different weight refinement methods, several variants are designed. We prove that our algorithm and three of its variants have the property of linear convergence. Experiments of Recommendation and Image Recovery are conducted to make empirical evaluation with promising results. The proposed algorithm takes only 700 seconds to process Yahoo Music dataset in PC, and achieves a root mean square error 24. 5 on the test set.

NeurIPS Conference 2003 Conference Paper

Salient Boundary Detection using Ratio Contour

Song Wang
Toshiro Kubota
Jeffrey Siskind

This paper presents a novel graph-theoretic approach, named ratio con- tour, to extract perceptually salient boundaries from a set of noisy bound- ary fragments detected in real images. The boundary saliency is deﬁned using the Gestalt laws of closure, proximity, and continuity. This pa- per ﬁrst constructs an undirected graph with two different sets of edges: solid edges and dashed edges. The weights of solid and dashed edges measure the local saliency in and between boundary fragments, respec- tively. Then the most salient boundary is detected by searching for an optimal cycle in this graph with minimum average weight. The proposed approach guarantees the global optimality without introducing any biases related to region area or boundary length. We collect a variety of images for testing the proposed approach with encouraging results.