Xiaoming Jin

AAAI Conference 2020 Conference Paper

Heterogeneous Transfer Learning with Weighted Instance-Correspondence Data

• Yuwei He
• Xiaoming Jin
• Guiguang Ding
• Yuchen Guo
• Jungong Han
• Jiyong Zhang
• Sicheng Zhao

Instance-correspondence (IC) data are potent resources for heterogeneous transfer learning (HeTL) due to the capability of bridging the source and the target domains at the instancelevel. To this end, people tend to use machine-generated IC data, because manually establishing IC data is expensive and primitive. However, existing IC data machine generators are not perfect and always produce the data that are not of high quality, thus hampering the performance of domain adaption. In this paper, instead of improving the IC data generator, which might not be an optimal way, we accept the fact that data quality variation does exist but find a better way to use the data. Specifically, we propose a novel heterogeneous transfer learning method named Transfer Learning with Weighted Correspondence (TLWC), which utilizes IC data to adapt the source domain to the target domain. Rather than treating IC data equally, TLWC can assign solid weights to each IC data pair depending on the quality of the data. We conduct extensive experiments on HeTL datasets and the state-of-the-art results verify the effectiveness of TLWC.

AAAI Conference 2019 Conference Paper

Adaptive Region Embedding for Text Classification

• Liuyu Xiang
• Xiaoming Jin
• Lan Yi
• Guiguang Ding

Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information, which is crucial to understanding texts. In this work, we propose the Adaptive Region Embedding to learn context representation to improve text classification. Specifically, a metanetwork is learned to generate a context matrix for each region, and each word interacts with its corresponding context matrix to produce the regional representation for further classification. Compared to previous models that are designed to capture context information, our model contains less parameters and is more flexible. We extensively evaluate our method on 8 benchmark datasets for text classification. The experimental results prove that our method achieves state-of-the-art performances and effectively avoids word ambiguity.

IJCAI Conference 2019 Conference Paper

Incremental Few-Shot Learning for Pedestrian Attribute Recognition

• Liuyu Xiang
• Xiaoming Jin
• Guiguang Ding
• Jungong Han
• Leida Li

Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a fixed set of attributes. They are unable to handle the incremental few-shot learning scenario, i. e. adapting a well-trained model to newly added attributes with scarce data, which commonly exists in the real world. In this work, we present a meta learning based method to address this issue. The core of our framework is a meta architecture capable of disentangling multiple attribute information and generalizing rapidly to new coming attributes. By conducting extensive experiments on the benchmark dataset PETA and RAP under the incremental few-shot setting, we show that our method is able to perform the task with competitive performances and low resource requirements.

IJCAI Conference 2018 Conference Paper

Automatic Gating of Attributes in Deep Structure

• Xiaoming Jin
• Tao He
• Cheng Wan
• Lan Yi
• Guiguang Ding
• Dou Shen

Deep structure has been widely applied in a large variety of fields for its excellence of representing data. Attributes are a unique type of data descriptions that have been successfully utilized in numerous tasks to enhance performance. However, to introduce attributes into deep structure is complicated and challenging, because different layers in deep structure accommodate features of different abstraction levels, while different attributes may naturally represent the data in different abstraction levels. This demands adaptively and jointly modeling of attributes and deep structure by carefully examining their relationship. Different from existing works that treat attributes straightforwardly as the same level without considering their abstraction levels, we can make better use of attributes in deep structure by properly connecting them. In this paper, we move forward along this new direction by proposing a deep structure named Attribute Gated Deep Belief Network (AG-DBN) that includes a tunable attribute-layer gating mechanism and automatically learns the best way of connecting attributes to appropriate hidden layers. Experimental results on a manually-labeled subset of ImageNet, a-Yahoo and a-Pascal data set justify the superiority of AG-DBN against several baselines including CNN model and other AG-DBN variants. Specifically, it outperforms the CNN model, VGG19, by significantly reducing the classification error from 26. 70% to 13. 56% on a-Pascal.

IJCAI Conference 2018 Conference Paper

Grouping Attribute Recognition for Pedestrian with Joint Recurrent Learning

• Xin Zhao
• Liufang Sang
• Guiguang Ding
• Yuchen Guo
• Xiaoming Jin

Pedestrian attributes recognition is to predict attribute labels of pedestrian from surveillance images, which is a very challenging task for computer vision due to poor imaging quality and small training dataset. It is observed that semantic pedestrian attributes to be recognised tend to show semantic or visual spatial correlation. Attributes can be grouped by the correlation while previous works mostly ignore this phenomenon. Inspired by Recurrent Neural Network (RNN)'s super capability of learning context correlations, this paper proposes an end-to-end Grouping Recurrent Learning (GRL) model that takes advantage of the intra-group mutual exclusion and inter-group correlation to improve the performance of pedestrian attribute recognition. Our GRL method starts with the detection of precise body region via Body Region Proposal followed by feature extraction from detected regions. These features, along with the semantic groups, are fed into RNN for recurrent grouping attribute recognition, where intra group correlations can be learned. Extensive empirical evidence shows that our GRL model achieves state-of-the-art results, based on pedestrian attribute datasets, i. e. standard PETA and RAP datasets.

AAAI Conference 2016 Conference Paper

Active Learning with Cross-Class Knowledge Transfer

• Yuchen Guo
• Guiguang Ding
• Yuqi Wang
• Xiaoming Jin

When there are insufficient labeled samples for training a supervised model, we can adopt active learning to select the most informative samples for human labeling, or transfer learning to transfer knowledge from related labeled data source. Combining transfer learning with active learning has attracted much research interest in recent years. Most existing works follow the setting where the class labels in source domain are the same as the ones in target domain. In this paper, we focus on a more challenging cross-class setting where the class labels are totally different in two domains but related to each other in an intermediary attribute space, which is barely investigated before. We propose a novel and effective method that utilizes the attribute representation as the seed parameters to generate the classification models for classes. And we propose a joint learning framework that takes into account the knowledge from the related classes in source domain, and the information in the target domain. Besides, it is simple to perform uncertainty sampling, a fundamental technique for active learning, based on the framework. We conduct experiments on three benchmark datasets and the results demonstrate the efficacy of the proposed method.

AAAI Conference 2016 Conference Paper

Multi-Domain Active Learning for Recommendation

• Zihan Zhang
• Xiaoming Jin
• Lianghao Li
• Guiguang Ding
• Qiang Yang

Recently, active learning has been applied to recommendation to deal with data sparsity on a single domain. In this paper, we propose an active learning strategy for recommendation to alleviate the data sparsity in a multi-domain scenario. Specifically, our proposed active learning strategy simultaneously consider both specific and independent knowledge over all domains. We use the expected entropy to measure the generalization error of the domain-specific knowledge and propose a variance-based strategy to measure the generalization error of the domain-independent knowledge. The proposed active learning strategy use a unified function to effectively combine these two measurements. We compare our strategy with five state-of-the-art baselines on five different multi-domain recommendation tasks, which are constituted by three real-world data sets. The experimental results show that our strategy performs significantly better than all the baselines and reduces human labeling efforts by at least 5. 6%, 8. 3%, 11. 8%, 12. 5% and 15. 4% on the five tasks, respectively.

AAAI Conference 2016 Conference Paper

Transductive Zero-Shot Recognition via Shared Model Space Learning

• Yuchen Guo
• Guiguang Ding
• Xiaoming Jin
• Jianmin Wang

Zero-shot Recognition (ZSR) is to learn recognition models for novel classes without labeled data. It is a challenging task and has drawn considerable attention in recent years. The basic idea is to transfer knowledge from seen classes via the shared attributes. This paper focus on the transductive ZSR, i. e. , we have unlabeled data for novel classes. Instead of learning models for seen and novel classes separately as in existing works, we put forward a novel joint learning approach which learns the shared model space (SMS) for models such that the knowledge can be effectively transferred between classes using the attributes. An effective algorithm is proposed for optimization. We conduct comprehensive experiments on three benchmark datasets for ZSR. The results demonstrates that the proposed SMS can significantly outperform the state-of-the-art related approaches which validates its efficacy for the ZSR task.

AAAI Conference 2015 Conference Paper

Gaussian Cardinality Restricted Boltzmann Machines

• Cheng Wan
• Xiaoming Jin
• Guiguang Ding
• Dou Shen

Restricted Boltzmann Machine (RBM) has been applied to a wide variety of tasks due to its advantage in feature extraction. Implementing sparsity constraint in the activated hidden units is an important improvement on RBM. The sparsity constraints in the existing methods are usually specified by users and are independent of the input data. However, the input data could be heterogeneous in content and thus naturally demand elastic and adaptive settings of the sparsity constraints. To solve this problem, we proposed a generalized model with adaptive sparsity constraint, named Gaussian Cardinality Restricted Boltzmann Machines (GC-RBM). In this model, the thresholds of hidden unit activations are decided by the input data and a given Gaussian distribution in the pre-training phase. We provide a principled method to train the GC-RBM with Gaussian prior. Experimental results on two real world data sets justify the effectiveness of the proposed method and its superiority over CaRBM in terms of classification accuracy.

AAAI Conference 2015 Conference Paper

Learning Predictable and Discriminative Attributes for Visual Recognition

• Yuchen Guo
• Guiguang Ding
• Xiaoming Jin
• Jianmin Wang

Utilizing attributes for visual recognition has attracted increasingly interest because attributes can effectively bridge the semantic gap between low-level visual features and high-level semantic labels. In this paper, we propose a novel method for learning predictable and discriminative attributes. Specifically, we require the learned attributes can be reliably predicted from visual features, and discover the inherent discriminative structure of data. In addition, we propose to exploit the intracategory locality of data to overcome the intra-category variance in visual data. We conduct extensive experiments on Animals with Attributes (AwA) and Caltech256 datasets, and the results demonstrate that the proposed method achieves state-of-the-art performance.

IJCAI Conference 2013 Conference Paper

Celebrity Recommendation with Collaborative Social Topic Regression

• Xuetao Ding
• Xiaoming Jin
• Yujia Li
• Lianghao Li

Recently how to recommend celebrities to the public becomes an interesting problem on the social network websites, such as Twitter and Tencent Weibo. In this paper, we proposed a unified hierarchical Bayesian model to recommend celebrities to the general users. Specifically, we proposed to leverage both social network and descriptions of celebrities to improve the prediction ability and recommendation interpretability. In our model, we combine topic model with matrix factorization for both social network of celebrities and user following action matrix. It works by regularizing celebrity factors through celebrity’s social network and descriptive words associated with each celebrity. We also proposed to incorporate different confidences for different dyadic contexts to handle the situation that only positive observations exist. We conducted experiments on two real-world datasets from Twitter and Tencent Weibo, which are the largest and second largest microblog websites in USA and China, respectively. The experiment results show that our model achieves a higher performance and provide more effective results than the state-of-art methods especially when recommending new celebrities. We also show that our model captures user intertests more precisely and gives better recommendation interpretability.

AAAI Conference 2012 Conference Paper

Topic Correlation Analysis for Cross-Domain Text Classification

• Lianghao Li
• Xiaoming Jin
• Mingsheng Long

Cross-domain text classification aims to automatically train a precise text classifier for a target domain by using labeled text data from a related source domain. To this end, the distribution gap between different domains has to be reduced. In previous works, a certain number of shared latent features (e. g. , latent topics, principal components, etc.) are extracted to represent documents from different domains, and thus reduce the distribution gap. However, only relying the shared latent features as the domain bridge may limit the amount of knowledge transferred. This limitation is more serious when the distribution gap is so large that only a small number of latent features can be shared between domains. In this paper, we propose a novel approach named Topic Correlation Analysis (TCA), which extracts both the shared and the domain-specific latent features to facilitate effective knowledge transfer. In TCA, all word features are first grouped into the shared and the domain-specific topics using a joint mixture model. Then the correlations between the two kinds of topics are inferred and used to induce a mapping between the domain-specific topics from different domains. Finally, both the shared and the mapped domain-specific topics are utilized to span a new shared feature space where the supervised knowledge can be effectively transferred. The experimental results on two real-world data sets justify the superiority of the proposed method over the stat-of-the-art baselines.

IJCAI Conference 2011 Conference Paper

Short Text Classification Improved by Learning Multi-Granularity Topics

• Mengen Chen
• Xiaoming Jin
• Dou Shen

Understanding the rapidly growing short text is very important. Short text is different from traditional documents in its shortness and sparsity, which hinders the application of conventional machine learning and text mining algorithms. Two major approaches have been exploited to enrich the representation of short text. One is to fetch contextual information of a short text to directly add more text; the other is to derive latent topics from existing large corpus, which are used as features to enrich the representation of short text. The latter approach is elegant and efficient in most cases. The major trend along this direction is to derive latent topics of certain granularity through well-known topic models such as latent Dirichlet allocation (LDA). However, topics of certain granularity are usually not sufficient to set up effective feature spaces. In this paper, we move forward along this direction by proposing an method to leverage topics at multiple granularity, which can model the short text more precisely. Taking short text classification as an example, we compared our proposed method with the state-of-the-art baseline over one open data set. Our method reduced the classification error by 20. 25% and 16. 68%respectively on two classifiers.

IJCAI Conference 2007 Conference Paper

• Yi Zhang
• Xiaoming Jin

This paper addresses the problem of concept sampling. In many real-world applications, a large collection of mixed concepts is available for decision making. However, the collection is often so large that it is difficult if not unrealistic to utilize those concepts directly, due to the domain-specific limitations of available space or time. This naturally yields the need for concept reduction. In this paper, we introduce the novel problem of concept sampling: to find the optimal subset of a large collection of mixed concepts in advance so that the performance of future decision making can be best preserved by selectively combining the concepts remained in the subset. The problem is formulized as an optimization process based on our derivation of a target function, which ties a clear connection between the composition of the concept subset and the expected error of future decision making upon the subset. Then, based on this target function, a sampling algorithm is developed and its effectiveness is discussed. Extensive empirical studies suggest that, the proposed concept sampling method well preserves the performance of decision making while dramatically reduces the number of concepts maintained and thus justify its usefulness in handling large-scale mixed concepts.