1 code implementation • 18 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.
1 code implementation • ACL 2020 • Yi-Ju Lu, Cheng-Te Li
This paper solves the fake news detection problem under a more realistic scenario on social media.
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.
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.
Ranked #4 on Zero-shot Relation Classification on Wiki-ZSL
1 code implementation • 4 Jan 2024 • Cheng-Te Li, Yu-Che Tsai, Chih-Yao Chen, Jay Chiehen Liao
In this survey, we dive into Tabular Data Learning (TDL) using Graph Neural Networks (GNNs), a domain where deep learning-based approaches have increasingly shown superior performance in both classification and regression tasks compared to traditional methods.
1 code implementation • 29 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.
1 code implementation • 26 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.
1 code implementation • 8 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.
1 code implementation • 26 Oct 2020 • Zhiqiang Zhong, Cheng-Te Li, Jun Pang
To fully unleash the power of HGRL, we present a novel framework, Personalised Meta-path based Heterogeneous Graph Neural Networks (PM-HGNN), to jointly generate meta-paths that are personalised for each individual node in a HIN and learn node representations for the target downstream task like node classification.
1 code implementation • 22 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.
1 code implementation • 1 Oct 2020 • Zhiqiang Zhong, Cheng-Te Li, Jun Pang
Specifically, a differentiable pooling operator is proposed to adaptively generate a multi-grained structure that involves meso- and macro-level semantic information in the graph.
1 code implementation • 16 Nov 2021 • Cheng Hsu, Cheng-Te Li, Diego Saez-Trumper, Yi-Zhan Hsu
Self-contradiction is one of the low-quality article types in Wikipedia.
1 code implementation • 12 Jul 2023 • Kuan-Chun Chen, Cheng-Te Li, Kuo-Jung Lee
Neural Architecture Search (NAS) has shown promising capability in learning text representation.
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.
no code implementations • 21 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.
no code implementations • ICLR 2018 • Yiping Song, Rui Yan, Cheng-Te Li, Jian-Yun Nie, Ming Zhang, Dongyan Zhao
Human-computer conversation systems have attracted much attention in Natural Language Processing.
no code implementations • 29 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.
no code implementations • 17 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.
no code implementations • 30 Apr 2022 • Cheng-Te Li, Cheng Hsu, Yang Zhang
We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness, is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups.
1 code implementation • 19 May 2023 • Karandeep Singh, Yu-Che Tsai, Cheng-Te Li, Meeyoung Cha, Shou-De Lin
Custom officials across the world encounter huge volumes of transactions.
no code implementations • 24 May 2023 • Yi-Zhan Xu, Chih-Yao Chen, Cheng-Te Li
We argue that image pairs should have varying degrees of similarity, and the negative samples should be allowed to be drawn from the entire dataset.
no code implementations • 25 May 2023 • Jay Chiehen Liao, Cheng-Te Li
This work presents a novel approach to tabular data prediction leveraging graph structure learning and graph neural networks.