Search Results for author: Cheng-Te Li

Found 16 papers, 8 papers with code

NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data

1 code implementation22 Jun 2021 I-Chung Hsieh, Cheng-Te Li

In this work, we propose a novel research task, adversarial defenses against GNN-based privacy attacks, and present a graph perturbation-based approach, NetFense, to achieve the goal.

FinGAT: Financial Graph Attention Networks for Recommending Top-K Profitable Stocks

1 code implementation18 Jun 2021 Yi-Ling Hsu, Yu-Che Tsai, Cheng-Te Li

Ignoring stock relationships will miss the information shared between stocks while using pre-defined relationships cannot depict the latent interactions or influence of stock prices between stocks.

Graph Attention Time Series

CoANE: Modeling Context Co-occurrence for Attributed Network Embedding

no code implementations17 Jun 2021 I-Chung Hsieh, Cheng-Te Li

The basic idea of CoANE is to model the context attributes that each node's involved diverse patterns, and apply the convolutional mechanism to encode positional information by treating each attribute as a channel.

Link Prediction Network Embedding +1

ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning

1 code implementation NAACL 2021 Chih-Yao Chen, Cheng-Te Li

While relation extraction is an essential task in knowledge acquisition and representation, and new-generated relations are common in the real world, less effort is made to predict unseen relations that cannot be observed at the training stage.

Multi-Task Learning Relation Extraction +1

RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation

1 code implementation29 Jan 2021 Cheng Hsu, Cheng-Te Li

In this work, we aim to present the holistic SR that simultaneously accommodates conventional, inductive, and transferable settings.

AGSTN: Learning Attention-adjusted Graph Spatio-Temporal Networks for Short-term Urban Sensor Value Forecasting

no code implementations29 Jan 2021 Yi-Ju Lu, Cheng-Te Li

Forecasting spatio-temporal correlated time series of sensor values is crucial in urban applications, such as air pollution alert, biking resource management, and intelligent transportation systems.

Time Series

Reinforcement Learning Enhanced Heterogeneous Graph Neural Network

no code implementations26 Oct 2020 Zhiqiang Zhong, Cheng-Te Li, Jun Pang

Specifically, RL-HGNN models the meta-path design process as a Markov Decision Process and uses a policy network to adaptively design a meta-path for each node to learn its effective representations.

Graph Representation Learning

HENIN: Learning Heterogeneous Neural Interaction Networks for Explainable Cyberbullying Detection on Social Media

1 code implementation EMNLP 2020 Hsin-Yu Chen, Cheng-Te Li

In the computational detection of cyberbullying, existing work largely focused on building generic classifiers that rely exclusively on text analysis of social media sessions.

Adaptive Multi-grained Graph Neural Networks

no code implementations1 Oct 2020 Zhiqiang Zhong, Cheng-Te Li, Jun Pang

Compared with the existing GNN models and pooling methods, AdamGNN enhances node representation with multi-grained semantics and avoids node feature and graph structure information loss during pooling.

Hierarchical Message-Passing Graph Neural Networks

no code implementations8 Sep 2020 Zhiqiang Zhong, Cheng-Te Li, Jun Pang

To deal with these two issues, we propose a novel Hierarchical Message-Passing Graph Neural Networks framework.

Community Detection Hierarchical structure +2

DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection

1 code implementation KDD 2020 Sundong Kim, Yu-Che Tsai, Karandeep Singh, Yeonsoo Choi, Etim Ibok, Cheng-Te Li, Meeyoung Cha

Intentional manipulation of invoices that lead to undervaluation of trade goods is the most common type of customs fraud to avoid ad valorem duties and taxes.

Fraud Detection Multi-target regression +1

A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm

1 code implementation26 Feb 2020 Sungwon Han, Yizhan Xu, Sungwon Park, Meeyoung Cha, Cheng-Te Li

Unsupervised embedding learning aims to extract good representation from data without the need for any manual labels, which has been a critical challenge in many supervised learning tasks.

Data Augmentation Image Classification

Towards a More Reliable Privacy-preserving Recommender System

no code implementations21 Nov 2017 Jia-Yun Jiang, Cheng-Te Li, Shou-De Lin

This paper proposes a privacy-preserving distributed recommendation framework, Secure Distributed Collaborative Filtering (SDCF), to preserve the privacy of value, model and existence altogether.

Recommendation Systems

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