no code implementations • 15 Mar 2024 • Tianxin Wei, Bowen Jin, Ruirui Li, Hansi Zeng, Zhengyang Wang, Jianhui Sun, Qingyu Yin, Hanqing Lu, Suhang Wang, Jingrui He, Xianfeng Tang
Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration.
1 code implementation • 9 Mar 2024 • Xiaowei Qian, Zhimeng Guo, Jialiang Li, Haitao Mao, Bingheng Li, Suhang Wang, Yao Ma
These datasets are thoughtfully designed to include relevant graph structures and bias information crucial for the fair evaluation of models.
no code implementations • 9 Mar 2024 • Bing He, Sreyashi Nag, Limeng Cui, Suhang Wang, Zheng Li, Rahul Goutam, Zhen Li, Haiyang Zhang
E-commerce platforms typically store and structure product information and search data in a hierarchy.
no code implementations • 24 Feb 2024 • Qian Ma, Hongliang Chi, Hengrui Zhang, Kay Liu, Zhiwei Zhang, Lu Cheng, Suhang Wang, Philip S. Yu, Yao Ma
The rise of self-supervised learning, which operates without the need for labeled data, has garnered significant interest within the graph learning community.
no code implementations • 18 Feb 2024 • Fali Wang, Runxue Bao, Suhang Wang, Wenchao Yu, Yanchi Liu, Wei Cheng, Haifeng Chen
Though Large Language Models (LLMs) have shown remarkable open-generation capabilities across diverse domains, they struggle with knowledge-intensive tasks.
no code implementations • 16 Feb 2024 • Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang
Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts.
1 code implementation • 13 Feb 2024 • Tianxiang Zhao, Xiang Zhang, Suhang Wang
Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data across various domains.
no code implementations • 6 Feb 2024 • Enyan Dai, Minhua Lin, Suhang Wang
PreGIP incorporates a task-free watermarking loss to watermark the embedding space of pretrained GNN encoder.
no code implementations • 4 Feb 2024 • Hongliang Chi, Cong Qi, Suhang Wang, Yao Ma
Yet, the excessive cost of labeling large-scale graphs led to a focus on active learning on graphs, which aims for effective data selection to maximize downstream model performance.
no code implementations • 18 Jan 2024 • Fali Wang, Tianxiang Zhao, Suhang Wang
Self-training has emerged as a widely popular framework to leverage the abundance of unlabeled data, which expands the training set by assigning pseudo-labels to selected unlabeled nodes.
no code implementations • 17 Jan 2024 • Teng Xiao, Suhang Wang
Probabilistic learning to rank (LTR) has been the dominating approach for optimizing the ranking metric, but cannot maximize long-term rewards.
no code implementations • 4 Jan 2024 • Haitong Luo, Xuying Meng, Suhang Wang, Hanyun Cao, Weiyao Zhang, Yequan Wang, Yujun Zhang
In this study, we present a novel approach called Spectral-based Complementary Graph Neural Networks (SComGNN) that utilizes the spectral properties of complementary item graphs.
1 code implementation • NeurIPS 2023 • Teng Xiao, Huaisheng Zhu, Zhengyu Chen, Suhang Wang
Experimental results show that the simple GraphACL significantly outperforms state-of-the-art graph contrastive learning and self-supervised learning methods on homophilic and heterophilic graphs.
no code implementations • 16 Oct 2023 • Junjie Xu, Enyan Dai, Dongsheng Luo, Xiang Zhang, Suhang Wang
Spectral Graph Neural Networks (GNNs) are gaining attention because they can surpass the limitations of message-passing GNNs by learning spectral filters that capture essential frequency information in graph data through task supervision.
no code implementations • 11 Oct 2023 • Bowen Jin, Hansi Zeng, Guoyin Wang, Xiusi Chen, Tianxin Wei, Ruirui Li, Zhengyang Wang, Zheng Li, Yang Li, Hanqing Lu, Suhang Wang, Jiawei Han, Xianfeng Tang
Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs.
1 code implementation • NeurIPS 2023 • Minhua Lin, Teng Xiao, Enyan Dai, Xiang Zhang, Suhang Wang
Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method in providing effective certifiable robustness and enhancing the robustness of any GCL model.
1 code implementation • 1 Oct 2023 • Teng Xiao, Zhengyu Chen, Donglin Wang, Suhang Wang
To compensate for this, in this paper, we present learning to propagate, a general learning framework that not only learns the GNN parameters for prediction but more importantly, can explicitly learn the interpretable and personalized propagate strategies for different nodes and various types of graphs.
no code implementations • 30 Sep 2023 • Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen
After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it.
1 code implementation • NeurIPS 2023 • Wei Jin, Haitao Mao, Zheng Li, Haoming Jiang, Chen Luo, Hongzhi Wen, Haoyu Han, Hanqing Lu, Zhengyang Wang, Ruirui Li, Zhen Li, Monica Xiao Cheng, Rahul Goutam, Haiyang Zhang, Karthik Subbian, Suhang Wang, Yizhou Sun, Jiliang Tang, Bing Yin, Xianfeng Tang
To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation.
1 code implementation • 10 Jul 2023 • Zhimeng Guo, Jialiang Li, Teng Xiao, Yao Ma, Suhang Wang
Despite their great performance in modeling graphs, recent works show that GNNs tend to inherit and amplify the bias from training data, causing concerns of the adoption of GNNs in high-stake scenarios.
no code implementations • 22 Jun 2023 • Yang Li, Kangbo Liu, Ranjan Satapathy, Suhang Wang, Erik Cambria
The objective of this study is to provide an overview of the current state-of-the-art in the field and highlight the latest trends in the development of recommender systems.
no code implementations • 21 Jun 2023 • Wanda Li, Wenhao Zheng, Xuanji Xiao, Suhang Wang
Our experimental results using both public and industrial datasets demonstrate that the proposed model significantly improves multi-task prediction performance compared to state-of-the-art methods, highlighting the importance of considering user lifecycle stages in recommendation systems.
no code implementations • 19 Jun 2023 • Huaisheng Zhu, Guoji Fu, Zhimeng Guo, Zhiwei Zhang, Teng Xiao, Suhang Wang
Graph Neural Networks (GNNs) have shown great power in various domains.
no code implementations • 14 Jun 2023 • Enyan Dai, Limeng Cui, Zhengyang Wang, Xianfeng Tang, Yinghan Wang, Monica Cheng, Bing Yin, Suhang Wang
Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs.
1 code implementation • 13 Jun 2023 • Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen
Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations.
no code implementations • 21 May 2023 • Huaisheng Zhu, Dongsheng Luo, Xianfeng Tang, Junjie Xu, Hui Liu, Suhang Wang
Directly adopting existing post-hoc explainers for explaining link prediction is sub-optimal because: (i) post-hoc explainers usually adopt another strategy or model to explain a target model, which could misinterpret the target model; and (ii) GNN explainers for node classification identify crucial subgraphs around each node for the explanation; while for link prediction, one needs to explain the prediction for each pair of nodes based on graph structure and node attributes.
1 code implementation • 3 Apr 2023 • Zhimeng Guo, Teng Xiao, Zongyu Wu, Charu Aggarwal, Hui Liu, Suhang Wang
To facilitate the development of this promising direction, in this survey, we categorize and comprehensively review papers on graph counterfactual learning.
1 code implementation • 11 Feb 2023 • Enyan Dai, Minhua Lin, Xiang Zhang, Suhang Wang
In particular, backdoor attack poisons the graph by attaching triggers and the target class label to a set of nodes in the training graph.
no code implementations • 7 Jan 2023 • Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making predictions.
no code implementations • 16 Dec 2022 • Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
To address this problem, we propose a new framework {\method} and design (1 a topology extractor, which automatically identifies the topology group for each instance with explicit memory cells, (2 a training modulator, which modulates the learning process of the target GNN model to prevent the case of topology-group-wise under-representation.
1 code implementation • 15 Oct 2022 • Junjie Xu, Enyan Dai, Xiang Zhang, Suhang Wang
Graph neural networks (GNNs) have achieved great success in various graph problems.
no code implementations • 5 Oct 2022 • Enyan Dai, Suhang Wang
Therefore, we study a novel problem of learning prototype-based self-explainable GNNs that can simultaneously give accurate predictions and prototype-based explanations on predictions.
no code implementations • 3 Aug 2022 • Shijie Zhou, Zhimeng Guo, Charu Aggarwal, Xiang Zhang, Suhang Wang
Therefore, in this paper, we study a novel problem of exploring disentangled representation learning for link prediction on heterophilic graphs.
no code implementations • 10 Jun 2022 • Tianxiang Zhao, Xiang Zhang, Suhang Wang
In many real-world scenarios, node classes are imbalanced, with some majority classes making up most parts of the graph.
no code implementations • 7 Jun 2022 • Teng Xiao, Zhengyu Chen, Suhang Wang
In this paper, we propose a theoretical understanding of why existing unbiased learning objectives work for unbiased recommendation.
no code implementations • 7 Jun 2022 • Teng Xiao, Zhengyu Chen, Zhimeng Guo, Zeyang Zhuang, Suhang Wang
This paper studies the problem of conducting self-supervised learning for node representation learning on graphs.
no code implementations • 27 May 2022 • Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
Two typical reasons of spurious explanations are identified: confounding effect of latent variables like distribution shift, and causal factors distinct from the original input.
no code implementations • 18 Apr 2022 • Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo, Hui Liu, Jiliang Tang, Suhang Wang
Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society.
no code implementations • 30 Mar 2022 • Huaisheng Zhu, Suhang Wang
The lack of sensitive attributes challenges many existing works.
no code implementations • 23 Feb 2022 • Tianxiang Zhao, Xiang Zhang, Suhang Wang
Concretely, these self-supervision tasks are enforced on a designed edge disentanglement module to be trained jointly with the downstream node classification task to encourage automatic edge disentanglement.
1 code implementation • 1 Jan 2022 • Enyan Dai, Wei Jin, Hui Liu, Suhang Wang
To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes.
1 code implementation • 15 Oct 2021 • Enyan Dai, Shijie Zhou, Zhimeng Guo, Suhang Wang
Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications.
Ranked #1 on Node Classification on Crocodile
1 code implementation • 26 Aug 2021 • Enyan Dai, Suhang Wang
Though many efforts are taken to improve the explainability of deep learning, they mainly focus on i. i. d data, which cannot be directly applied to explain the predictions of GNNs because GNNs utilize both node features and graph topology to make predictions.
no code implementations • 7 Aug 2021 • Wenqi Fan, Wei Jin, Xiaorui Liu, Han Xu, Xianfeng Tang, Suhang Wang, Qing Li, Jiliang Tang, JianPing Wang, Charu Aggarwal
Despite the great success, recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs.
no code implementations • 22 Jun 2021 • Yang Li, Wei Zhao, Erik Cambria, Suhang Wang, Steffen Eger
Therefore, in this paper, we introduce a new capsule network with graph routing to learn both relationships, where capsules in each layer are treated as the nodes of a graph.
no code implementations • 8 Jun 2021 • Enyan Dai, Kai Shu, Yiwei Sun, Suhang Wang
We propose a novel generative framework named as ADDES which can synthesize high-quality labeled data for target classification tasks by learning from data with inexact supervision and the relations between inexact supervision and target classes.
1 code implementation • 8 Jun 2021 • Enyan Dai, Charu Aggarwal, Suhang Wang
Graph Neural Networks (GNNs) have achieved promising results for semi-supervised learning tasks on graphs such as node classification.
no code implementations • 27 May 2021 • Yuqing Hu, Xiaoyuan Cheng, Suhang Wang, Jianli Chen, Tianxiang Zhao, Enyan Dai
After discussion, it is found that data-driven models integrated engineering or physical knowledge can significantly improve the urban building energy simulation.
1 code implementation • 29 Apr 2021 • Tianxiang Zhao, Enyan Dai, Kai Shu, Suhang Wang
Though the sensitive attribute of each data sample is unknown, we observe that there are usually some non-sensitive features in the training data that are highly correlated with sensitive attributes, which can be used to alleviate the bias.
2 code implementations • 16 Mar 2021 • Tianxiang Zhao, Xiang Zhang, Suhang Wang
This task is non-trivial, as previous synthetic minority over-sampling algorithms fail to provide relation information for newly synthesized samples, which is vital for learning on graphs.
no code implementations • 16 Mar 2021 • Tianxiang Zhao, Xianfeng Tang, Xiang Zhang, Suhang Wang
For example, we can easily build graphs representing peoples' shared music tastes and those representing co-purchase behavior, but a well paired dataset is much more expensive to obtain.
1 code implementation • 23 Nov 2020 • Tsung-Yu Hsieh, Suhang Wang, Yiwei Sun, Vasant Honavar
Time series data is prevalent in a wide variety of real-world applications and it calls for trustworthy and explainable models for people to understand and fully trust decisions made by AI solutions.
2 code implementations • 3 Sep 2020 • Enyan Dai, Suhang Wang
Though extensive studies of fair classification have been conducted on i. i. d data, methods to address the problem of discrimination on non-i. i. d data are rather limited.
1 code implementation • 1 Sep 2020 • Thai Le, Suhang Wang, Dongwon Lee
In recent years, the proliferation of so-called "fake news" has caused much disruptions in society and weakened the news ecosystem.
no code implementations • 28 Jun 2020 • Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Yiqi Wang, Jiliang Tang, Charu Aggarwal, Prasenjit Mitra, Suhang Wang
Pseudo labels increase the chance of connecting to labeled neighbors for low-degree nodes, thus reducing the biases of GCNs from the data perspective.
1 code implementation • 17 Jun 2020 • Wei Jin, Tyler Derr, Haochen Liu, Yiqi Wang, Suhang Wang, Zitao Liu, Jiliang Tang
Thus, we seek to harness SSL for GNNs to fully exploit the unlabeled data.
no code implementations • 10 Jun 2020 • Xianfeng Tang, Yozen Liu, Neil Shah, Xiaolin Shi, Prasenjit Mitra, Suhang Wang
In this paper, we study a novel problem of explainable user engagement prediction for social network Apps.
3 code implementations • 20 May 2020 • Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, Jiliang Tang
A natural idea to defend adversarial attacks is to clean the perturbed graph.
1 code implementation • 27 Jan 2020 • Enyan Dai, Yiwei Sun, Suhang Wang
Nowadays, Internet is a primary source of attaining health information.
1 code implementation • 2 Jan 2020 • Kai Shu, Suhang Wang, Dongwon Lee, Huan Liu
In recent years, disinformation including fake news, has became a global phenomenon due to its explosive growth, particularly on social media.
no code implementations • 22 Nov 2019 • Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Charu Aggarwal, Prasenjit Mitra, Suhang Wang
Thus, jointly modeling local and global temporal dynamics is very promising for MTS forecasting with missing values.
1 code implementation • 5 Nov 2019 • Thai Le, Suhang Wang, Dongwon Lee
Despite the recent development in the topic of explainable AI/ML for image and text data, the majority of current solutions are not suitable to explain the prediction of neural network models when the datasets are tabular and their features are in high-dimensional vectorized formats.
1 code implementation • 7 Oct 2019 • Huaxiu Yao, Chuxu Zhang, Ying WEI, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh V. Chawla, Zhenhui Li
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
no code implementations • 14 Sep 2019 • Yiwei Sun, Suhang Wang, Xianfeng Tang, Tsung-Yu Hsieh, Vasant Honavar
Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes.
1 code implementation • 20 Aug 2019 • Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang
To optimize PA-GNN for a poisoned graph, we design a meta-optimization algorithm that trains PA-GNN to penalize perturbations using clean graphs and their adversarial counterparts, and transfers such ability to improve the robustness of PA-GNN on the poisoned graph.
Ranked #25 on Node Classification on Pubmed
no code implementations • 20 Aug 2019 • Yiwei Sun, Suhang Wang, Tsung-Yu Hsieh, Xianfeng Tang, Vasant Honavar
Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e. g., friendship, shared interests in music, etc.)
no code implementations • 10 Jun 2019 • Yao Ma, Suhang Wang, Tyler Derr, Lingfei Wu, Jiliang Tang
Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification.
no code implementations • 30 Apr 2019 • Kai Shu, Xinyi Zhou, Suhang Wang, Reza Zafarani, Huan Liu
In an attempt to understand connections between user profiles and fake news, first, we measure users' sharing behaviors on social media and group representative users who are more likely to share fake and real news; then, we perform a comparative analysis of explicit and implicit profile features between these user groups, which reveals their potential to help differentiate fake news from real news.
1 code implementation • 30 Apr 2019 • Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang
To apply graph neural networks for the graph classification task, approaches to generate the \textit{graph representation} from node representations are demanded.
Ranked #1 on Graph Classification on NC1
2 code implementations • 21 Mar 2019 • Kai Shu, Deepak Mahudeswaran, Suhang Wang, Huan Liu
In an attempt to understand the correlations between news propagation networks and fake news, first, we build a hierarchical propagation network from macro-level and micro-level of fake news and true news; second, we perform a comparative analysis of the propagation network features of linguistic, structural and temporal perspectives between fake and real news, which demonstrates the potential of utilizing these features to detect fake news; third, we show the effectiveness of these propagation network features for fake news detection.
Social and Information Networks
7 code implementations • 5 Sep 2018 • Kai Shu, Deepak Mahudeswaran, Suhang Wang, Dongwon Lee, Huan Liu
However, fake news detection is a non-trivial task, which requires multi-source information such as news content, social context, and dynamic information.
Social and Information Networks
no code implementations • 18 Aug 2018 • Yao Ma, Suhang Wang, Charu C. Aggarwal, Dawei Yin, Jiliang Tang
Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video.
Social and Information Networks
4 code implementations • 20 Dec 2017 • Kai Shu, Suhang Wang, Huan Liu
Recent Social and Psychology studies show potential importance to utilize social media data: 1) Confirmation bias effect reveals that consumers prefer to believe information that confirms their existing stances; 2) Echo chamber effect suggests that people tend to follow likeminded users and form segregated communities on social media.
Social and Information Networks
no code implementations • 15 Sep 2017 • Yang Li, Quan Pan, Suhang Wang, Haiyun Peng, Tao Yang, Erik Cambria
The majority of existing semi-supervised VAEs utilize a classifier to exploit label information, where the parameters of the classifier are introduced to the VAE.
no code implementations • 14 Sep 2017 • Fred Morstatter, Kai Shu, Suhang Wang, Huan Liu
We apply our solution to sentiment analysis, a task that can benefit from the emoji calibration technique we use in this work.
6 code implementations • 7 Aug 2017 • Kai Shu, Amy Sliva, Suhang Wang, Jiliang Tang, Huan Liu
First, fake news is intentionally written to mislead readers to believe false information, which makes it difficult and nontrivial to detect based on news content; therefore, we need to include auxiliary information, such as user social engagements on social media, to help make a determination.
no code implementations • 21 Jul 2016 • Yilin Wang, Suhang Wang, Jiliang Tang, Neil O'Hare, Yi Chang, Baoxin Li
Understanding human actions in wild videos is an important task with a broad range of applications.
no code implementations • CVPR 2016 • Yilin Wang, Suhang Wang, Jiliang Tang, Huan Liu, Baoxin Li
However, pointwise labels in image classification and tag annotation are inherently related to the pairwise labels.
2 code implementations • 29 Jan 2016 • Jundong Li, Kewei Cheng, Suhang Wang, Fred Morstatter, Robert P. Trevino, Jiliang Tang, Huan Liu
To facilitate and promote the research in this community, we also present an open-source feature selection repository that consists of most of the popular feature selection algorithms (\url{http://featureselection. asu. edu/}).