1 code implementation • NeurIPS 2023 • Han Liu, Zhi Xu, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Hongyang Chen, Hong Yu, Xianchao Zhang
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible.
no code implementations • 29 Oct 2023 • Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wei Wang, Hongyang Chen, Hong Yu, Xianchao Zhang
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction.
no code implementations • 5 Oct 2023 • Aadi Kothari, Tony Tohme, Xiaotong Zhang, Kamal Youcef-Toumi
We propose a novel human motion prediction framework that incorporates human joint constraints and scene constraints in a Gaussian Process Regression (GPR) model to predict human motion over a set time horizon.
no code implementations • 26 Mar 2023 • Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Fenglong Ma, Xiao-Ming Wu, Hongyang Chen, Hong Yu, Xianchao Zhang
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain.
Few-Shot Image Classification Few-Shot Text Classification +1
no code implementations • 14 Jun 2022 • Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Junjie Sun, Hong Yu, Xianchao Zhang
Multi-label aspect category detection allows a given review sentence to contain multiple aspect categories, which is shown to be more practical in sentiment analysis and attracting increasing attention.
no code implementations • 5 Jun 2022 • Han Liu, Siyang Zhao, Xiaotong Zhang, Feng Zhang, Junjie Sun, Hong Yu, Xianchao Zhang
Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data.
1 code implementation • 12 Feb 2022 • Fan Lu, Qimai Li, Bo Liu, Xiao-Ming Wu, Xiaotong Zhang, Fuyu Lv, Guli Lin, Sen Li, Taiwei Jin, Keping Yang
Our approach can be seamlessly integrated with existing latent space based methods and be potentially applied in any product retrieval method that uses purchase history to model user preferences.
no code implementations • Findings (EMNLP) 2021 • Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Xianchao Zhang
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems.
no code implementations • CVPR 2021 • Xianchao Zhang, Ziyang Cheng, Xiaotong Zhang, Han Liu
In this paper, we propose a novel variant of GAN, Posterior Promoted GAN (P2GAN), which promotes generator with the real information in the posterior distribution produced by discriminator.
no code implementations • 24 Jan 2021 • Tailin Liang, John Glossner, Lei Wang, Shaobo Shi, Xiaotong Zhang
We discuss trade-offs in element-wise, channel-wise, shape-wise, filter-wise, layer-wise and even network-wise pruning.
1 code implementation • ACL 2020 • Guangfeng Yan, Lu Fan, Qimai Li, Han Liu, Xiaotong Zhang, Xiao-Ming Wu, Albert Y. S. Lam
User intent classification plays a vital role in dialogue systems.
1 code implementation • IJCNLP 2019 • Han Liu, Xiaotong Zhang, Lu Fan, Xu Fu, i, Qimai Li, Xiao-Ming Wu, Albert Y. S. Lam
With the burgeoning of conversational AI, existing systems are not capable of handling numerous fast-emerging intents, which motivates zero-shot intent classification.
no code implementations • 27 Sep 2019 • Han Liu, Xianchao Zhang, Xiaotong Zhang, Qimai Li, Xiao-Ming Wu
However, there are two issues in existing possible world based algorithms: (1) They rely on all the possible worlds and treat them equally, but some marginal possible worlds may cause negative effects.
1 code implementation • 26 Sep 2019 • Qimai Li, Xiaotong Zhang, Han Liu, Quanyu Dai, Xiao-Ming Wu
Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors.
no code implementations • 25 Sep 2019 • Qimai Li, Xiaotong Zhang, Han Liu, Xiao-Ming Wu
Graph convolutional neural networks have demonstrated promising performance in attributed graph learning, thanks to the use of graph convolution that effectively combines graph structures and node features for learning node representations.
1 code implementation • 4 Jun 2019 • Xiaotong Zhang, Han Liu, Qimai Li, Xiao-Ming Wu
Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes.
Ranked #3 on Graph Clustering on Cora
1 code implementation • CVPR 2019 • Qimai Li, Xiao-Ming Wu, Han Liu, Xiaotong Zhang, Zhichao Guan
However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods.