Search Results for author: Zhonghai Wu

Found 17 papers, 6 papers with code

Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model

1 code implementation COLING 2022 Sixing Wu, Ying Li, Ping Xue, Dawei Zhang, Zhonghai Wu

However, a dialogue is always aligned to a lot of retrieved fact candidates; as a result, the linearized text is always lengthy and then significantly increases the burden of using PLMs.

Dialogue Generation Language Modelling

More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge

1 code implementation EMNLP 2021 Sixing Wu, Ying Li, Minghui Wang, Dawei Zhang, Yang Zhou, Zhonghai Wu

Despite achieving remarkable performance, previous knowledge-enhanced works usually only use a single-source homogeneous knowledge base of limited knowledge coverage.

Dialogue Generation

Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning

no code implementations20 Oct 2022 Xiaoyi Chen, Baisong Xin, Shengfang Zhai, Shiqing Ma, Qingni Shen, Zhonghai Wu

This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks.

Backdoor Attack Contrastive Learning +2

TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene

no code implementations5 Oct 2022 Luyuan Xie, Yan Zhong, Lin Yang, Zhaoyu Yan, Zhonghai Wu, Junjie Wang

In our experiments, the performance gain brought by GridMask is stronger than spectrum augmentation in ASCs.

AutoML Data Augmentation

Kallima: A Clean-label Framework for Textual Backdoor Attacks

no code implementations3 Jun 2022 Xiaoyi Chen, Yinpeng Dong, Zeyu Sun, Shengfang Zhai, Qingni Shen, Zhonghai Wu

Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks.

Revisiting Graph based Social Recommendation: A Distillation Enhanced Social Graph Network

no code implementations Proceedings of the ACM Web Conference 2022 Ying Li, Ye Tao, Su Zhang, Zhirong Hou, Zhonghai Wu

We train a model that integrates information from the user-item interaction graph and the user-user social graph and train two auxiliary models that only use one of the above graphs respectively.

Knowledge Distillation Recommendation Systems

A Vertical Federated Learning Framework for Horizontally Partitioned Labels

no code implementations18 Jun 2021 Wensheng Xia, Ying Li, Lan Zhang, Zhonghai Wu, Xiaoyong Yuan

To address these challenges, we propose a novel vertical federated learning framework named Cascade Vertical Federated Learning (CVFL) to fully utilize all horizontally partitioned labels to train neural networks with privacy-preservation.

Federated Learning

Relation-Aware Neighborhood Matching Model for Entity Alignment

1 code implementation15 Dec 2020 Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yingpeng Du

Besides comparing neighbor nodes when matching neighborhood, we also try to explore useful information from the connected relations.

Entity Alignment Knowledge Graphs

BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements

no code implementations1 Jun 2020 Xiaoyi Chen, Ahmed Salem, Dingfan Chen, Michael Backes, Shiqing Ma, Qingni Shen, Zhonghai Wu, Yang Zhang

In this paper, we perform a systematic investigation of backdoor attack on NLP models, and propose BadNL, a general NLP backdoor attack framework including novel attack methods.

Backdoor Attack BIG-bench Machine Learning +1

Representation Learning with Ordered Relation Paths for Knowledge Graph Completion

1 code implementation IJCNLP 2019 Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang song, Tao Zhang

Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.

Ranked #3 on Link Prediction on FB15k (MR metric)

Link Prediction Representation Learning

An influence-based fast preceding questionnaire model for elderly assessments

no code implementations22 Nov 2017 Tong Mo, Rong Zhang, Weiping Li, Jingbo Zhang, Zhonghai Wu, Wei Tan

The practice in an elderly-care company shows that the FPQM can reduce the number of attributes by 90. 56% with a prediction accuracy of 98. 39%.

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