Yang Yang

Dr. Yang Yang


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
TFTaoran Fang
Taoran Fang
ZXZhiqing Xiao
Zhiqing Xiao
CWChunping Wang
Chunping Wang
JXJiarong Xu
Jiarong Xu
YYYang Yang
Yang Yang
YYYang Yang
Yang Yang
Graph Neural Networks (GNNs) are powerful tools for graph representation learning. Despite their rapid development, GNNs also face some challenges, such as over-fitting, over-smoothing, and non-robustness. Previous works indicate that these problems can be alleviated by random dropping methods, which integrate augmented data into models by randomly masking parts of the input. However, some open problems of random dropping on GNNs remain to be solved. First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models. Second, augmented data introduced to GNNs causes the incomplete coverage of parameters and unstable training process. Third, there is no theoretical analysis on the effectiveness of random dropping methods on GNNs. In this paper, we propose a novel random dropping method called DropMessage, which performs dropping operations directly on the propagated messages during the message-passing process. More importantly, we find that DropMessage provides a unified framework for most existing random dropping methods, based on which we give theoretical analysis of their effectiveness. Furthermore, we elaborate the superiority of DropMessage: it stabilizes the training process by reducing sample variance; it keeps information diversity from the perspective of information theory, enabling it become a theoretical upper bound of other methods. To evaluate our proposed method, we conduct experiments that aims for multiple tasks on five public datasets and two industrial datasets with various backbone models. The experimental results show that DropMessage has the advantages of both effectiveness and generalization, and can significantly alleviate the problems mentioned above. A detailed version with full appendix can be found on arXiv: https://arxiv.org/abs/2204.10037.

24 June 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YYYang Yang
Yang Yang
YXYuhong Xu
Yuhong Xu
YSYizhou Sun
Yizhou Sun
YDYuxiao Dong
Yuxiao Dong
FWFei Wu
Fei Wu
YZYueting Zhuang
Yueting Zhuang
The rapid development of modern communication technologies---in particular, (mobile) phone communications---has largely facilitated human social interactions and information exchange. However, the emergence of telemarketing frauds can significantly dissipate individual fortune and social wealth, resulting in potential slow down or damage to economics. In this work, we propose to spot telemarketing frauds, with an emphasis on unveiling the precise fraud phenomenon and the strategies that are used by fraudsters to precisely select targets. To study this problem, we employ a one-month complete dataset of telecommunication metadata in Shanghai with 54 million users and 698 million call logs. Through our study, we find that user's information has been seriously leaked, and fraudsters have preference over the target user's age and activity in mobile network. We further propose a novel semi-supervised learning framework to distinguish fraudsters from non-fraudsters. Experimental results on a real-world data show that our approach outperforms several state-of-the-art algorithms in accuracy of detecting fraudsters (e.g., +0.58 in terms of F1). We believe that our study can potentially inform policymaking for government and mobile service providers.

7 July 2021 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
ZCZiqiang Cheng
Ziqiang Cheng
YYYang Yang
Yang Yang
SJShuo Jiang
Shuo Jiang
WHWenjie Hu
Wenjie Hu
ZYZhangchi Ying
Zhangchi Ying
CWChunping Wang
Chunping Wang
Time series modeling has attracted great research interests in the last decades. Among the literature, shapelet-based models aim to extract representative subsequences, and could offer explanatory insights. In order to capture the shapelet dynamics and evolutions, we propose a novel framework of bridging time series representation learning and graph modeling, with two different implementations. We first formulate the process of extracting time-aware shapelets, then briefly introduce the key idea of transforming time series data into shapelet evolution graphs, to model the shapelet evolutionary patterns. A straightforward solution is to enumerate all possible shapelet transitions among adjacent time series segments, and apply a random-walk-based graph embedding algorithm to learn the time series representations (Time2Graph). We further extend Time2Graph by adopting graph attention mechanism to refine the procedure of modeling shapelet evolutions, namely Time2Graph+. Specifically, we transform each time series data into a unique and unweighted shapelet graph, and use GAT to automatically capture the correlations between shapelets. Experimental results show the significant improvements of Time2Graph+, and extensive observational analysis demonstrate the effectiveness and interpretability brought by attentions. Furthermore, the success of online deployment of Time2Graph+ model in State Grid of China validates the whole framework in the real-world application.

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
ZCZiwei Chai
Ziwei Chai
YYYang Yang
Yang Yang
JDJiawang Dan
Jiawang Dan
STSheng Tian
Sheng Tian
CMChanghua Meng
Changhua Meng
YSYifei Sun
Yifei Sun
Anti-money laundering (AML) systems play a critical role in safeguarding global economy. As money laundering is considered as one of the top group crimes, there is a crucial need to discover money laundering sub-network behind a particular money laundering transaction for a robust AML system. However, existing rule-based methods for money laundering sub-network discovery is heavily based on domain knowledge and may lag behind the modus operandi of launderers. Therefore, in this work, we first address the money laundering sub-network discovery problem with a neural network based approach, and propose an AML framework AMAP equipped with an adaptive sub-network proposer. In particular, we design an adaptive sub-network proposer guided by a supervised contrastive loss to discriminate money laundering transactions from massive benign transactions. We conduct extensive experiments on real-word datasets in AliPay of Ant Group. The result demonstrates the effectiveness of our AMAP in both money laundering transaction detection and money laundering sub-network discovering. The learned framework which yields money laundering sub-network from massive transaction network leads to a more comprehensive risk coverage and a deeper insight to money laundering strategies.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
CPChenglu Pan
Chenglu Pan
JXJiarong Xu
Jiarong Xu
YYYue Yu
Yue Yu
ZYZiqi Yang
Ziqi Yang
QWQingbiao Wu
Qingbiao Wu
YYYang Yang
Yang Yang
Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data privacy. Yet, current efforts overlook a key issue: agents are self-interested and would hesitant to share data without fair and satisfactory incentives. This paper is the first endeavor to address this issue by studying the incentive mechanism for graph federated learning. We identify a unique phenomenon in graph federated learning: the presence of agents posing potential harm to the federation and agents contributing with delays. This stands in contrast to previous FL incentive mechanisms that assume all agents contribute positively and in a timely manner. In view of this, this paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff. To achieve this, we first introduce an agent valuation function aimed at quantifying agent contributions through the introduction of two criteria: gradient alignment and graph diversity. Moreover, due to the high heterogeneity in graph federated learning, striking a balance between accuracy and fairness becomes particularly crucial. We introduce motif prototypes to enhance accuracy, communicated between the server and agents, enhancing global model aggregation and aiding agents in local model optimization. Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.

19 January 2017 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
BWBoya Wu
Boya Wu
JJJia Jia
Jia Jia
YYYang Yang
Yang Yang
PZPeijun Zhao
Peijun Zhao
JTJie Tang
Jie Tang
QTQi Tian
Qi Tian
Social images, which are images uploaded and shared on social networks, are used to express users' emotions. Inferring emotional tags from social images is of great importance; it can benefit many applications, such as image retrieval and recommendation. Whereas previous related research has primarily focused on exploring image visual features, we aim to address this problem by studying whether user demographics make a difference regarding users' emotional tags of social images. We first consider how to model the emotions of social images. Then, we investigate how user demographics, such as gender, marital status, and occupation, are related to the emotional tags of social images. A partially labeled factor graph model named the demographics factor graph model (D-FGM) is proposed to leverage the uncovered patterns. Experiments on a data set collected from the world's largest image sharing website Flickr 1 confirm the accuracy of the proposed model. We also find some interesting phenomena. For example, men and women have different patterns to tag “anger” for social images.