no code implementations • 26 Apr 2024 • Yichuan Li, Kaize Ding, Jianling Wang, Kyumin Lee
With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation.
1 code implementation • 10 Apr 2024 • Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
In this paper, we explore the hypothesis that LLMs process concepts of varying complexities in different layers, introducing the idea of "Concept Depth" to suggest that more complex concepts are typically acquired in deeper layers.
2 code implementations • 17 Feb 2024 • Shuhan Liu, Kaize Ding
Distribution shifts on graphs -- the data distribution discrepancies between training and testing a graph machine learning model, are often ubiquitous and unavoidable in real-world scenarios.
1 code implementation • 24 Jan 2024 • Wenjing Chang, Kay Liu, Kaize Ding, Philip S. Yu, Jianjun Yu
Firstly, by coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies.
no code implementations • NeurIPS 2023 • Yixin Liu, Kaize Ding, Qinghua Lu, Fuyi Li, Leo Yu Zhang, Shirui Pan
In this paper, we investigate a new challenging problem, explainable GLAD, where the learning objective is to predict the abnormality of each graph sample with corresponding explanations, i. e., the vital subgraph that leads to the predictions.
1 code implementation • 23 Oct 2023 • Yichuan Li, Kaize Ding, Kyumin Lee
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately.
no code implementations • 25 Jul 2023 • Suraj Jyothi Unni, Paras Sheth, Kaize Ding, Huan Liu, K. Selcuk Candan
Discovering causal relationships in complex socio-behavioral systems is challenging but essential for informed decision-making.
1 code implementation • 17 Jun 2023 • Song Wang, Xingbo Fu, Kaize Ding, Chen Chen, Huiyuan Chen, Jundong Li
In this way, the server can exploit the computational power of all clients and train the model on a larger set of data samples among all clients.
no code implementations • 14 Jun 2023 • Shuyi Chen, Kaize Ding, Shixiang Zhu
Graph neural networks have shown impressive capabilities in solving various graph learning tasks, particularly excelling in node classification.
no code implementations • 9 Jun 2023 • Zhen Tan, Ruocheng Guo, Kaize Ding, Huan Liu
Our approach utilizes a pretrained graph transformer as the encoder and injects virtual nodes as soft prompts in the embedding space, which can be optimized with few-shot labels in novel classes to modulate node embeddings for each specific FSNC task.
1 code implementation • 29 May 2023 • Yixin Liu, Kaize Ding, Jianling Wang, Vincent Lee, Huan Liu, Shirui Pan
Accordingly, we propose D$^2$PT, a dual-channel GNN framework that performs long-range information propagation not only on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
no code implementations • 27 May 2023 • Kaize Ding, Albert Jiongqian Liang, Bryan Perrozi, Ting Chen, Ruoxi Wang, Lichan Hong, Ed H. Chi, Huan Liu, Derek Zhiyuan Cheng
Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval.
no code implementations • 18 May 2023 • Xiongxiao Xu, Kaize Ding, Canyu Chen, Kai Shu
However, the work exploring limited labeled anomalies and a large amount of unlabeled nodes in graphs to detect anomalies is rather limited.
no code implementations • 17 May 2023 • Haohui Wang, Baoyu Jing, Kaize Ding, Yada Zhu, Wei Cheng, Si Zhang, Yonghui Fan, Liqing Zhang, Dawei Zhou
To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i. e., each task corresponds to the prediction of one particular class.
no code implementations • 25 Jan 2023 • Baoyu Jing, Yuchen Yan, Kaize Ding, Chanyoung Park, Yada Zhu, Huan Liu, Hanghang Tong
Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs.
1 code implementation • 6 Jan 2023 • Song Wang, Yushun Dong, Kaize Ding, Chen Chen, Jundong Li
Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i. e., meta-training classes) and then generalize to classes with limited labeled nodes (i. e., meta-test classes).
1 code implementation • 24 Dec 2022 • Ujun Jeong, Kaize Ding, Lu Cheng, Ruocheng Guo, Kai Shu, Huan Liu
Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society.
Ranked #1 on Graph Classification on UPFD-POL
1 code implementation • 11 Dec 2022 • Zhen Tan, Song Wang, Kaize Ding, Jundong Li, Huan Liu
More recently, inspired by the development of graph self-supervised learning, transferring pretrained node embeddings for few-shot node classification could be a promising alternative to meta-learning but remains unexposed.
1 code implementation • 8 Nov 2022 • Yixin Liu, Kaize Ding, Huan Liu, Shirui Pan
As a pioneering work in unsupervised graph-level OOD detection, we build a comprehensive benchmark to compare our proposed approach with different state-of-the-art methods.
no code implementations • 26 Aug 2022 • Kaize Ding, Elnaz Nouri, Guoqing Zheng, Huan Liu, Ryen White
The success of graph neural networks on graph-based web mining highly relies on abundant human-annotated data, which is laborious to obtain in practice.
1 code implementation • 23 Jun 2022 • Song Wang, Kaize Ding, Chuxu Zhang, Chen Chen, Jundong Li
Then we transfer such knowledge to the classes with limited labeled nodes via our proposed task-adaptive modules.
2 code implementations • 21 Jun 2022 • Kay Liu, Yingtong Dou, Yue Zhao, Xueying Ding, Xiyang Hu, Ruitong Zhang, Kaize Ding, Canyu Chen, Hao Peng, Kai Shu, Lichao Sun, Jundong Li, George H. Chen, Zhihao Jia, Philip S. Yu
To bridge this gap, we present--to the best of our knowledge--the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights.
no code implementations • 29 Mar 2022 • Zhen Tan, Kaize Ding, Ruocheng Guo, Huan Liu
Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis.
no code implementations • 17 Mar 2022 • Chuxu Zhang, Kaize Ding, Jundong Li, Xiangliang Zhang, Yanfang Ye, Nitesh V. Chawla, Huan Liu
In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge.
1 code implementation • 17 Feb 2022 • Kaize Ding, Yancheng Wang, Yingzhen Yang, Huan Liu
In general, the contrastive learning process in GCL is performed on top of the representations learned by a graph neural network (GNN) backbone, which transforms and propagates the node contextual information based on its local neighborhoods.
1 code implementation • 16 Feb 2022 • Kaize Ding, Zhe Xu, Hanghang Tong, Huan Liu
In this survey, we formally formulate the problem of graph data augmentation and further review the representative techniques and their applications in different deep graph learning problems.
no code implementations • 28 Dec 2021 • Jianling Wang, Kaize Ding, Ziwei Zhu, James Caverlee
Session-based recommender systems aim to improve recommendations in short-term sessions that can be found across many platforms.
1 code implementation • 23 Dec 2021 • Zhen Tan, Kaize Ding, Ruocheng Guo, Huan Liu
The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems.
1 code implementation • 18 Dec 2021 • Kaize Ding, Jianling Wang, James Caverlee, Huan Liu
Inspired by the extensive success of deep learning, graph neural networks (GNNs) have been proposed to learn expressive node representations and demonstrated promising performance in various graph learning tasks.
no code implementations • EMNLP 2021 • Kaize Ding, Dingcheng Li, Alexander Hanbo Li, Xing Fan, Chenlei Guo, Yang Liu, Huan Liu
In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with weak supervision data.
1 code implementation • 13 Jul 2021 • Jianling Wang, Kaize Ding, James Caverlee
A fundamental challenge for sequential recommenders is to capture the sequential patterns of users toward modeling how users transit among items.
no code implementations • 12 Jun 2021 • Kaize Ding, Jianling Wang, Jundong Li, James Caverlee, Huan Liu
Graphs are widely used to model the relational structure of data, and the research of graph machine learning (ML) has a wide spectrum of applications ranging from drug design in molecular graphs to friendship recommendation in social networks.
no code implementations • 31 May 2021 • Ujun Jeong, Kaize Ding, Huan Liu
The growing use of social media has led to drastic changes in our decision-making.
1 code implementation • 26 Apr 2021 • Yushun Dong, Kaize Ding, Brian Jalaian, Shuiwang Ji, Jundong Li
Existing efforts can be mainly categorized as spectral-based and spatial-based methods.
2 code implementations • 22 Feb 2021 • Kaize Ding, Qinghai Zhou, Hanghang Tong, Huan Liu
Network anomaly detection aims to find network elements (e. g., nodes, edges, subgraphs) with significantly different behaviors from the vast majority.
1 code implementation • 8 Dec 2020 • Kai Shu, Yichuan Li, Kaize Ding, Huan Liu
The existing text generation methods either afford limited supplementary information or lose consistency between the input and output which makes the synthetic news less trustworthy.
1 code implementation • EMNLP 2020 • Kaize Ding, Jianling Wang, Jundong Li, Dingcheng Li, Huan Liu
Text classification is a critical research topic with broad applications in natural language processing.
no code implementations • 14 Jul 2020 • Kai Shu, Amrita Bhattacharjee, Faisal Alatawi, Tahora Nazer, Kaize Ding, Mansooreh Karami, Huan Liu
The creation, dissemination, and consumption of disinformation and fabricated content on social media is a growing concern, especially with the ease of access to such sources, and the lack of awareness of the existence of such false information.
1 code implementation • 10 Jul 2020 • Xuan Shan, Chuanjie Liu, Yiqian Xia, Qi Chen, Yusi Zhang, Kaize Ding, Yaobo Liang, Angen Luo, Yuxiang Luo
Deep matching models aim to facilitate search engines retrieving more relevant documents by mapping queries and documents into semantic vectors in the first-stage retrieval.
1 code implementation • 23 Jun 2020 • Kaize Ding, Jianling Wang, Jundong Li, Kai Shu, Chenghao Liu, Huan Liu
By constructing a pool of semi-supervised node classification tasks to mimic the real test environment, GPN is able to perform \textit{meta-learning} on an attributed network and derive a highly generalizable model for handling the target classification task.
no code implementations • 19 Aug 2019 • Kaize Ding, Yichuan Li, Jundong Li, Chenghao Liu, Huan Liu
Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on different graph learning tasks.
2 code implementations • 2019 SIAM International Conference on Data Mining (SDM) 2019 • Kaize Ding, Jundong Li, Rohit Bhanushali, Huan Liu
In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data.