AI Open最新文献

Network embedding (NE) aims to learn low-dimensional vectors for nodes while preserving the network’s essential properties (e.g., attributes and structure). Previous methods have been proposed to learn node representations with encouraging achievements. Recent research has shown that the hierarchical label has potential value in seeking latent hierarchical structures and learning more effective classification information. Nevertheless, most existing network embedding methods either focus on the network without the hierarchical label, or the learning process of hierarchical structure for labels is separate from the network structure. Learning node embedding with the hierarchical label suffers from two challenges: (1) Fusing hierarchical labels and network is still an arduous task. (2) The data volume imbalance under different hierarchical labels is more noticeable than flat labels. This paper proposes a Hierarchical Label and Attributed Network Structure Fusion model(HANS), which realizes the fusion of hierarchical labels and nodes through attributes and the attention-based fusion module. Particularly, HANS designs a directed hierarchy structure encoder for modeling label dependencies in three directions (parent–child, child–parent, and sibling) to strengthen the co-occurrence information between labels of different frequencies and reduce the impact of the label imbalance. Experiments on real-world datasets demonstrate that the proposed method achieves significantly better performance than the state-of-the-art algorithms.

Conventional machine learning (ML) relies heavily on manual design from machine learning experts to decide learning tasks, data, models, optimization algorithms, and evaluation metrics, which is labor-intensive, time-consuming, and cannot learn autonomously like humans. In education science, self-directed learning, where human learners select learning tasks and materials on their own without requiring hands-on guidance, has been shown to be more effective than passive teacher-guided learning. Inspired by the concept of self-directed human learning, we introduce the principal concept of Self-directed Machine Learning (SDML) and propose a framework for SDML. Specifically, we design SDML as a self-directed learning process guided by self-awareness, including internal awareness and external awareness. Our proposed SDML process benefits from self task selection, self data selection, self model selection, self optimization strategy selection and self evaluation metric selection through self-awareness without human guidance. Meanwhile, the learning performance of the SDML process serves as feedback to further improve self-awareness. We propose a mathematical formulation for SDML based on multi-level optimization. Furthermore, we present case studies together with potential applications of SDML, followed by discussing future research directions. We expect that SDML could enable machines to conduct human-like self-directed learning and provide a new perspective towards artificial general intelligence.

The information age enables people to obtain news online through various channels, yet in the meanwhile making false news spread at unprecedented speed. Fake news exerts detrimental effects for it impairs social stability and public trust, which calls for increasing demand for fake news detection (FND). As deep learning (DL) achieves tremendous success in various domains, it has also been leveraged in FND tasks and surpasses traditional machine learning based methods, yielding state-of-the-art performance. In this survey, we present a complete review and analysis of existing DL based FND methods that focus on various features such as news content, social context, and external knowledge. We review the methods under the lines of supervised, weakly supervised, and unsupervised methods. For each line, we systematically survey the representative methods utilizing different features. Then, we introduce several commonly used FND datasets and give a quantitative analysis of the performance of the DL based FND methods over these datasets. Finally, we analyze the remaining limitations of current approaches and highlight some promising future directions.

The aim of human motion modeling is to understand human behaviors and create reasonable human motion like real people given different priors. With the development of deep learning, researchers tend to leverage data-driven methods to improve the performance of traditional motion modeling methods. In this paper, we present a comprehensive survey of recent human motion modeling researches. We discuss three categories of human motion modeling researches: human motion prediction, humanoid motion control and cross-modal motion synthesis and provide a detailed review over existing methods. Finally, we further discuss the remaining challenges in human motion modeling.

Graph neural networks (GNNs) have been widely adopted for modeling graph-structure data. Most existing GNN studies have focused on designing different strategies to propagate information over the graph structures. After systematic investigations, we observe that the propagation step in GNNs matters, but its resultant performance improvement is insensitive to the location where we apply it. Our empirical examination further shows that the performance improvement brought by propagation mostly comes from a phenomenon of distribution alignment, i.e., propagation over graphs actually results in the alignment of the underlying distributions between the training and test sets. The findings are instrumental to understand GNNs, e.g., why decoupled GNNs can work as good as standard GNNs.¹

The mainstream domain adaptation (DA) methods transfer the supervised source domain knowledge to the unsupervised or semi-supervised target domain, so as to assist the classification task in the target domain. Usually the supervision only contains the class label of the object. However, when human beings recognize a new object, they will not only learn the class label of the object, but also correlate the object to its parent class, and use this information to learn the similarities and differences between child classes. Our model utilizes hierarchical relations via making the parent class label of labeled data (all the source domain data and part of target domain data) as a part of supervision to guide prototype learning module vbfd to learn the parent class information encoding, so that the prototypes of the same parent class are closer in the prototype space, which leads to better classification results. Inspired by this mechanism, we propose a Hierarchical relation aided Semi-Supervised Domain Adaptation (HSSDA) method which incorporates the hierarchical relations into the Semi-Supervised Domain Adaptation (SSDA) method to improve the classification results of the model. Our model performs well on the DomainNet dataset, and gets the state-of-the-art results in the semi-supervised DA problem.

As an important way to alleviate information overload, a recommender system aims to filter out irrelevant information for users and provides them items that they may be interested in. In recent years, an increasing amount of works have been proposed to introduce auxiliary information in recommender systems to alleviate data sparsity and cold-start problems. Among them, heterogeneous information networks (HIN)-based recommender systems provide a unified approach to fuse various auxiliary information, which can be combined with mainstream recommendation algorithms to effectively enhance the performance and interpretability of models, and thus have been applied in many kinds of recommendation tasks. This paper provides a comprehensive and systematic survey of HIN-based recommender systems, including four aspects: concepts, methods, applications, and resources. Specifically, we firstly introduce the concepts related to recommender systems, heterogeneous information networks and HIN-based recommendation. Secondly, we present more than 70 methods categorized according to models or application scenarios, and describe representative methods symbolically. Thirdly, we summarize the benchmark datasets and open source code. Finally, we discuss several potential research directions and conclude our survey.

As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods in detail according to the above categories. Further, we also introduce their applications in NLP tasks as well as the challenges. Some useful resources are provided in Appendix A.

Recently, prompt tuning has been widely applied to stimulate the rich knowledge in pre-trained language models (PLMs) to serve NLP tasks. Although prompt tuning has achieved promising results on some few-class classification tasks, such as sentiment classification and natural language inference, manually designing prompts is cumbersome. Meanwhile, generating prompts automatically is also difficult and time-consuming. Therefore, obtaining effective prompts for complex many-class classification tasks still remains a challenge. In this paper, we propose to encode the prior knowledge of a classification task into rules, then design sub-prompts according to the rules, and finally combine the sub-prompts to handle the task. We name this Prompt Tuning method with Rules “PTR”. Compared with existing prompt-based methods, PTR achieves a good trade-off between effectiveness and efficiency in building prompts. We conduct experiments on three many-class classification tasks, including relation classification, entity typing, and intent classification. The results show that PTR outperforms both vanilla and prompt tuning baselines, indicating the effectiveness of utilizing rules for prompt tuning. The source code of PTR is available at https://github.com/thunlp/PTR.