Search Results for author: Kaize Ding

Found 21 papers, 10 papers with code

A Simple Yet Effective Pretraining Strategy for Graph Few-shot Learning

no code implementations29 Mar 2022 Zhen Tan, Kaize Ding, Ruocheng Guo, Huan Liu

Recently, increasing attention has been devoted to the graph few-shot learning problem, where the target novel classes only contain a few labeled nodes.

Contrastive Learning Data Augmentation +2

Few-Shot Learning on Graphs: A Survey

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

Structural and Semantic Contrastive Learning for Self-supervised Node Representation Learning

no code implementations17 Feb 2022 Kaize Ding, Yancheng Wang, Yingzhen Yang, Huan Liu

Graph Contrastive Learning (GCL) recently has drawn much research interest for learning generalizable, transferable, and robust node representations in a self-supervised fashion.

Contrastive Learning Representation Learning

Data Augmentation for Deep Graph Learning: A Survey

no code implementations16 Feb 2022 Kaize Ding, Zhe Xu, Hanghang Tong, Huan Liu

To counter the data noise and data scarcity issues in deep graph learning (DGL), increasing graph data augmentation research has been conducted lately.

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.

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 +1

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

Weakly-supervised Graph Meta-learning for 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 +3

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

no 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 +1

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

1 code implementation 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

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