396 citations · 605 across the 23 of their papers we have counts for
23 papers
Boosting Few-Shot Text Classification via Distribution Estimation
Han Liu, Feng Zhang, Xiaotong Zhang +6
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 repres…
Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning
Guangyuan Shi, Qimai Li, Wenlong Zhang +2
A fundamental challenge for multi-task learning is that different tasks may conflict with each other when they are solved jointly, and a cause of this phenomenon is conflicting gra…
Simple yet Effective Gradient-Free Graph Convolutional Networks
Yulin Zhu, Xing Ai, Qimai Li +2
Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. Compared with nonlinear Graph Neural Network (GNN) models,…
A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds
Wenlong Zhang, Guangyuan Shi, Yihao Liu +2
Degradation models play an important role in Blind super-resolution (SR). The classical degradation model, which mainly involves blur degradation, is too simple to simulate real-wo…
New Intent Discovery with Pre-training and Contrastive Learning
Yuwei Zhang, Haode Zhang, Li-Ming Zhan +2
New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and servi…
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization
Haode Zhang, Haowen Liang, Yuwei Zhang +4
It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language…
Modeling User Behavior with Graph Convolution for Personalized Product Search
Fan Lu, Qimai Li, Bo Liu +7
User preference modeling is a vital yet challenging problem in personalized product search. In recent years, latent space based methods have achieved state-of-the-art performance b…
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
Guangyuan Shi, Jiaxin Chen, Wenlong Zhang +2
This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing…
Effectiveness of Pre-training for Few-shot Intent Classification
Haode Zhang, Yuwei Zhang, Li-Ming Zhan +4
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a…
Adaptation-Agnostic Meta-Training
Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu +1
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters…
Embedding-based Product Retrieval in Taobao Search
Sen Li, Fuyu Lv, Taiwei Jin +5
Nowadays, the product search service of e-commerce platforms has become a vital shopping channel in people's life. The retrieval phase of products determines the search system's qu…
Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Li-Ming Zhan, Haowen Liang, Bo Liu +3
Out-of-scope intent detection is of practical importance in task-oriented dialogue systems. Since the distribution of outlier utterances is arbitrary and unknown in the training st…
SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
Bo Liu, Li-Ming Zhan, Li Xu +3
Medical visual question answering (Med-VQA) has tremendous potential in healthcare. However, the development of this technology is hindered by the lacking of publicly-available and…
M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
Menghan Wang, Yujie Lin, Guli Lin +2
Combining graph representation learning with multi-view data (side information) for recommendation is a trend in industry. Most existing methods can be categorized as \emph{multi-v…
Self-Supervised Graph Representation Learning via Global Context Prediction
Zhen Peng, Yixiang Dong, Minnan Luo +2
To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supe…
Variational Metric Scaling for Metric-Based Meta-Learning
Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu +1
Metric-based meta-learning has attracted a lot of attention due to its effectiveness and efficiency in few-shot learning. Recent studies show that metric scaling plays a crucial ro…
Clustering Uncertain Data via Representative Possible Worlds with Consistency Learning
Han Liu, Xianchao Zhang, Xiaotong Zhang +2
Clustering uncertain data is an essential task in data mining for the internet of things. Possible world based algorithms seem promising for clustering uncertain data. However, the…
Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs
Qimai Li, Xiaotong Zhang, Han Liu +2
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 com…
Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution
Quanyu Dai, Xiao-Ming Wu, Jiaren Xiao +2
This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in…
Attributed Graph Clustering via Adaptive Graph Convolution
Xiaotong Zhang, Han Liu, Qimai Li +1
Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes. Recent progress on graph convolutional networks has proved that g…
Label Efficient Semi-Supervised Learning via Graph Filtering
Qimai Li, Xiao-Ming Wu, Han Liu +2
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and u…
Large Margin Few-Shot Learning
Yong Wang, Xiao-Ming Wu, Qimai Li +4
The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-sh…
Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
Qimai Li, Zhichao Han, Xiao-Ming Wu
Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semisupervised learning, a recent important development is graph con…