Search Results for author: Kaize Ding

Found 44 papers, 26 papers with code

TSI-Bench: Benchmarking Time Series Imputation

3 code implementations18 Jun 2024 Wenjie Du, Jun Wang, Linglong Qian, Yiyuan Yang, Fanxing Liu, Zepu Wang, Zina Ibrahim, Haoxin Liu, Zhiyuan Zhao, Yingjie Zhou, Wenjia Wang, Kaize Ding, Yuxuan Liang, B. Aditya Prakash, Qingsong Wen

Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings.

Benchmarking Imputation +2

Avoiding Copyright Infringement via Machine Unlearning

1 code implementation16 Jun 2024 Guangyao Dou, Zheyuan Liu, Qing Lyu, Kaize Ding, Eric Wong

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns.

General Knowledge Machine Unlearning

Empowering Large Language Models for Textual Data Augmentation

no code implementations26 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.

Data Augmentation Few-Shot Learning

Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?

1 code implementation10 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.

Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs

2 code implementations17 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.

Multitask Active Learning for Graph Anomaly Detection

1 code implementation24 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.

Active Learning Graph Anomaly Detection +2

Towards Self-Interpretable Graph-Level Anomaly Detection

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.

Graph Anomaly Detection

GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs

1 code implementation23 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.

Contrastive Learning Graph Neural Network +3

UPREVE: An End-to-End Causal Discovery Benchmarking System

no code implementations25 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.

Benchmarking Causal Discovery +1

Federated Few-shot Learning

1 code implementation17 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.

Federated Learning Few-Shot Learning

Uncertainty-Aware Robust Learning on Noisy Graphs

no code implementations14 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.

Graph Learning Graph Neural Network +1

Virtual Node Tuning for Few-shot Node Classification

no code implementations9 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.

Classification Graph Representation Learning +2

Learning Strong Graph Neural Networks with Weak Information

1 code implementation29 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.

Graph Learning

MetaGAD: Learning to Meta Transfer for Few-shot Graph Anomaly Detection

no code implementations18 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.

Graph Anomaly Detection

Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization

no code implementations17 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.

Classification Contrastive Learning +1

STERLING: Synergistic Representation Learning on Bipartite Graphs

no code implementations25 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.

Contrastive Learning Graph Representation Learning +1

Few-shot Node Classification with Extremely Weak Supervision

1 code implementation6 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).

Classification Meta-Learning +1

Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

1 code implementation24 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.

Fake News Detection

Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

1 code implementation11 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.

Classification Contrastive Learning +4

GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

1 code implementation8 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.

Contrastive Learning Data Augmentation +2

Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity

no code implementations26 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.

Data Augmentation Node Classification

Task-Adaptive Few-shot Node Classification

1 code implementation23 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.

Classification Few-Shot Learning +2

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

2 code implementations21 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.

Anomaly Detection Benchmarking +2

Supervised Graph Contrastive Learning for Few-shot Node Classification

no code implementations29 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.

Classification Contrastive Learning +4

Few-Shot Learning on Graphs

no code implementations17 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.

Few-Shot Learning Graph Mining +1

Eliciting Structural and Semantic Global Knowledge in Unsupervised Graph Contrastive Learning

1 code implementation17 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.

Contrastive Learning Graph Neural Network +1

Data Augmentation for Deep Graph Learning: A Survey

1 code implementation16 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.

Data Augmentation Graph Learning

Session-based Recommendation with Hypergraph Attention Networks

no code implementations28 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.

Session-Based Recommendations

Graph Few-shot Class-incremental Learning

1 code implementation23 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.

Few-Shot Class-Incremental Learning Incremental Learning +2

Meta Propagation Networks for Graph Few-shot Semi-supervised Learning

1 code implementation18 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.

Graph Learning Meta-Learning

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

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.

Language Modelling Meta-Learning +2

Sequential Recommendation for Cold-start Users with Meta Transitional Learning

1 code implementation13 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.

Few-Shot Learning Sequential Recommendation +1

Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification

no code implementations12 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.

Classification Graph Learning +4

Few-shot Network Anomaly Detection via Cross-network Meta-learning

2 code implementations22 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.

Anomaly Detection Few-Shot Learning

Fact-Enhanced Synthetic News Generation

1 code implementation8 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.

News Generation Text Summarization +1

Combating Disinformation in a Social Media Age

no code implementations14 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.

GLOW : Global Weighted Self-Attention Network for Web Search

1 code implementation10 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.

Document Ranking Information Retrieval +2

Graph Prototypical Networks for Few-shot Learning on Attributed Networks

1 code implementation23 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.

Classification Drug Discovery +5

Feature Interaction-aware Graph Neural Networks

no code implementations19 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.

Graph Learning Representation Learning

Deep Anomaly Detection on Attributed Networks

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.

Anomaly Detection Attribute

Cannot find the paper you are looking for? You can Submit a new open access paper.