学术成果

一. 发表论文

1.

论文题目

A Probabilistic Graphical Model Based on Neural-symbolic Reasoning for Visual Relationship Detection

论文主题词

Deep learning ,Knowledge engineering ,Visualization ,Graphical models ,Uncertainty ,Markov processes ,Probabilistic logic

论文作者

Dongran Yu; Bo Yang; Qianhao Wei; Anchen Li; Shirui Pan

论文摘要

This paper aims to leverage symbolic knowledge to improve the performance and interpretability of the Visual Relationship Detection (VRD) models. Existing VRD methods based on deep learning suffer from the problems of poor performance on insufficient labeled examples and lack of interpretability. To overcome the aforementioned weaknesses, we integrate symbolic knowledge into deep learning models and propose a bi-level probabilistic graphical reasoning framework called BPGR. Specifically, in the highlevel structure, we take the objects and relationships detected by the VRD model as hidden variables (reasoning results); In the low-level structure of BPGR, we use Markov Logic Networks (MLNs) to project First-Order Logic (FOL) as observed variables (symbolic knowledge) to correct error reasoning results. We adopt a variational EM algorithm for optimization. Experiments results show that our BPGR improves the performance of the VRD models. In particular, BPGR can also provide easy-to-understand insights for reasoning results to show interpretability.

CVPR 2022


2.

论文题目

Hypercomplex Graph Collaborative Filtering

论文主题词

Recommendation, Collaborative Filtering, Hypercomplex Spaces,Graph Convolutional Networks, Cayley–Dickson Construction.

论文作者

Anchen Li; Bo Yang; Huan Huo; Farookh Hussain

论文摘要:

Hypercomplex algebras are well-developed in the area of mathematics. Recently, several hypercomplex recommendation approaches have been proposed and yielded great success. However, two vital issues have not been well-considered in existing hypercomplex recommenders. First, these methods are only designed for specific and low-dimensional hypercomplex algebras (e.g., complex and quaternion algebras), ignoring the exploration and utilization of high-dimensional ones. Second, most recommenders treat every user-item interaction as an isolated data instance, without considering high-order collaborative relationships.

To bridge these gaps, in this paper, we propose a novel recommendation framework named HyperComplex Graph Collaborative Filtering (HCGCF). To study the high-dimensional hypercomplex algebras, we introduce Cayley–Dickson construction which utilizes a recursive process to define hypercomplex algebras and their mathematical operations. Based on Cayley–Dickson construction, we devise a hypercomplex graph convolution operator to learn user and item representations. Specifically, the operator models both the neighborhood summary and interaction relations with neighbors in hypercomplex spaces, effectively exploiting the high-order connectivity in the user-item bipartite graph. To the best of our knowledge, it is the first time that Cayley-Dickson construction and graph convolution techniques have been explicitly discussed and used in hypercomplex recommender systems. Compared with several state-of-the-art recommender baselines, HCGCF achieves superior performance in both click-through rate prediction and top-K recommendation on three real-world datasets.

WWW 2022


3.

论文题目:

PNMTA: A Pretrained Network Modulation and Task Adaptation Approach for User Cold-Start Recommendation

论文主题词:

Recommender systems, Cold-start problem, Meta learning, Transfer learning

论文作者:

Haoyu Pang,Fausto Giunchiglia,Ximing Li, Renchu Guan,Xiaoyue Feng

WWW 2022

论文摘要:User cold-start recommendation is a serious problem that limits the performance of recommender systems (RSs). Recent studies have focused on treating this issue as a few-shot problem and seeking solutions with model-agnostic meta-learning (MAML). Such methods regard making recommendations for one user as a task and adapt to new users with a few steps of gradient updates on the metamodel. However, none of those methods consider the limitation of user representation learning imposed by the special task setting of MAML-based RSs. And they learn a common meta-model for all users while ignoring the implicit grouping distribution induced by the correlation differences among users. In response to the above problems, we propose a pretrained network modulation and task adaptation approach (PNMTA) for user cold-start recommendation. In the pretraining stage, a pretrained model is obtained with nonmeta-learning methods to achieve better user representation and generalization, which can also transfer the learned knowledge to the meta-learning stage for modulation. During the meta-learning stage, an encoder modulator is utilized to realize the memorization and correction of prior parameters for the meta-learning task, and a predictor modulator is introduced to condition the model initialization on the task identity for adaptation steps. In addition, PNMTA can also make use of the existing non-cold-start users for pretraining. Comprehensive experiments on two benchmark datasets demonstrate that our model can achieve significant and consistent improvements against other state-of-the-art methods.


4.

论文题目

Optimal resource allocation with spatiotemporal transmission discovery for efective disease control

论文主题词

COVID-19, Omicron outbreak, Densely populated regions, Spatiotemporal transmission risk, Optimal resource allocation, Integrative case management, Efective disease control

论文作者

Jinfu Ren,Mutong Liu,Yang Liu &Jiming Liu 

Abstract

Background: The new waves of COVID-19 outbreaks caused by the SARS-CoV-2 Omicron variant are developing rapidly and getting out of control around the world, especially in highly populated regions. The healthcare capacity (especially the testing resources, vaccination coverage, and hospital capacity) is becoming extremely insufcient as the demand will far exceed the supply. To address this time-critical issue, we need to answer a key question: How can we efectively infer the daily transmission risks in diferent districts using machine learning methods and thus lay out the corresponding resource prioritization strategies, so as to alleviate the impact of the Omicron outbreaks?

Methods: We propose a computational method for future risk mapping and optimal resource allocation based on the quantitative characterization of spatiotemporal transmission patterns of the Omicron variant. We collect the publicly available data from the ofcial website of the Hong Kong Special Administrative Region (HKSAR) Government and the study period in this paper is from December 27, 2021 to July 17, 2022 (including a period for future prediction). First, we construct the spatiotemporal transmission intensity matrices across diferent districts based on infection case records. With the constructed cross-district transmission matrices, we forecast the future risks of various locations daily by means of the Gaussian process. Finally, we develop a transmission-guided resource prioritization strategy that enables efective control of Omicron outbreaks under limited capacity.

IDP 2022

Results: We conduct a comprehensive investigation of risk mapping and resource allocation in Hong Kong, China.The maps of the district-level transmission risks clearly demonstrate the irregular and spatiotemporal varying patterns of the risks, making it difcult for the public health authority to foresee the outbreaks and plan the responses accordingly. With the guidance of the inferred transmission risks, the developed prioritization strategy enables the optimal testing resource allocation for integrative case management (including case detection, quarantine, and further treatment), i.e., with the 300,000 testing capacity per day; it could reduce the infection peak by 87.1% compared with the population-based allocation strategy (case number reduces from 20,860 to 2689) and by 24.2% compared with the case-based strategy (case number reduces from 3547 to 2689), signifcantly alleviating the burden of the healthcare system.

Conclusions: Computationally characterizing spatiotemporal transmission patterns allows for the efective risk mapping and resource prioritization; such adaptive strategies are of critical importance in achieving timely outbreak control under insufcient capacity. The proposed method can help guide public-health responses not only to the Omicron outbreaks but also to the potential future outbreaks caused by other new variants. Moreover, the investigation conducted in Hong Kong, China provides useful suggestions on how to achieve efective disease control with insufcient capacity in other highly populated countries and regions


5.

论文题目

Worker Selection Towards Data Completion for Online Sparse Crowdsensing

论文作者

Wenbin Liu; En Wang; Yongjian Yang; Jie Wu

论文主题词

Online Sparse Crowdsensing, Matrix Completion, Worker Selection.

IEEE 2022

论文摘要:

As a cost-effective paradigm, Sparse Crowdsensing aims to recruit workers to perform a part of sensing tasks and infer the rest, which has broad applications, including environmental monitoring, urban sensing, etc. In most cases, workers will participate in real time, and thus their sensing data are coming dynamically. Taking full advantage of the online coming data to complete the full sensing map is an important problem for Sparse Crowdsensing. However, for data completion, the importance of data collected from different spatio-temporal areas is usually different and time-varying. For example, the newly obtained data in the center is often more important than the old ones from edges. Moreover, the area importance may also influence the following worker selection, i.e., selecting suitable workers to actively sense important areas (instead of passively waiting for given data) for improving completion accuracy. To this end, in this paper, we propose a framework for online Sparse Crowdsensing, called OS-MCS, which consists of three parts: matrix completion, importance estimation, and worker selection. We start from the dynamically coming data and propose an online matrix completion algorithm with spatio-temporal constraints. Based on that, we estimate the spatio-temporal area importance by conducting a reinforcement learning-based up-to-date model. Finally, we utilize the prophet secretary problem to select suitable workers to sense important areas for accurate completion in an online manner. Extensive experiments on real-world data sets show the effectiveness of our proposals.


6.

论文题目

Privacy-Preserving Online Task Assignment in Spatial Crowdsourcing: A Graph-based Approach

论文作者

Hengzhi Wang; En Wang; Yongjian Yang; Jie Wu; Falko Dressler

论文主题词

Spatial crowdsourcing, privacy protection, online task assignment, one-worker-many-tasks assignment.

IEEE 2022

论文摘要:

Recently, the growing popularity of Spatial Crowdsourcing (SC), allowing untrusted platforms to obtain a great quantity of information about workers and tasks’ locations, has raised numerous privacy concerns. In this paper, we investigate the privacy-preserving task assignment in the online scenario, where workers and tasks arrive at the platform in real time and tasks should be assigned to workers immediately. Traditional online task assignments usually make a benchmark to decide the following task assignment. However, when location privacy is considered, the benchmark does not work anymore. Hence, how to assign tasks in real time based on workers and tasks’ obfuscated locations is a challenging problem. Especially when many tasks could be assigned to one worker, path planning should be considered, making the assignment more challenging. To this end, we propose a Planar Laplace distribution based Privacy mechanism (PLP) to obfuscate real locations of workers and tasks, where the obfuscation does not change the ranking of these locations’ relative distances. Furthermore, we design a Thresholdbased Online task Assignment mechanism (TOA), which could deal with the one-worker-many-tasks assignment and achieve a satisfactory competitive ratio. Simulations based on two realworld datasets show that the proposed algorithm consistently outperforms the state-of-the-art approach.


7.

论文题目

Spatial-Temporal Interval Aware Sequential POI Recommendation

论文作者

En Wang; Yiheng Jiang; Yuanbo Xu; Liang Wang; Yongjian Yang

论文主题词:

sequential POI recommendation, positional encoding, attention mechanism

论文摘要

The past flourishing years of sequential point-of-interest (POI) recommendation began with the introduction of Self-Attention Network (SAN), which quickly superseded CNN or RNN as the state-of-the-art backbone. To realize the fine-grained users’ behavior patterns modeling, recent works utilize modified attention mechanisms or neural network layers to process spatial-temporal factors. However, due to the significant increase on either model’s parameter scale or computational burden, we argue that these methods can be further improved. In this paper, we exploit two lightweight approaches, Time Aware Position Encoder (TAPE) and Interval Aware Attention Block (IAAB), to impel SAN by considering the spatial-temporal intervals among POIs separately, where requiring neither extra parameters nor high computational cost. On the one hand, TAPE, adjusting the positions in sequences based on the timestamps dynamically and generating positional representations with sinusoidal transformation, can enhance sequence representations to reflect both the absolute order and relative temporal proximity among all POIs. On the other hand, IAAB, point-wise adding the scaled spatial-temporal intervals to the attention map, can promote the attention mechanism attaching importance to the spatial relation among all POIs under the constraints of time conditions and providing more explainable recommendation. We integrate these two modules into SAN and propose a Spatial-Temporal Interval-Aware sequential POI recommender, namely STiSAN, as an end-to-end deployment. Experimental results based on three public LBSN datasets and one real-world city transportation dataset demonstrate STiSAN’s superior performance (average 13.01% improvement against the strongest baseline). Moreover, we validate the extensibility and interpretability of TAPE and IAAB through metric evaluation and visualization separately.

ICDE 2022


8.

论文题目

Few-shot Node Classification on Attributed Networks with Graph Meta-learning

论文作者

Yonghao Liu, Mengyu Li, Ximing Li, Fausto Giunchiglia, Xiaoyue Feng, Renchu Guan

论文关键字

graph neural networks, few-shot learning, node classification

SIGIR 2022

代码链接

论文摘要

Attributed networks, as a manifestation of data in non-Euclidean domains, have a wide range of applications in the real world, such as molecular property prediction, social network analysis and anomaly detection. Node classification, as a fundamental research problem in attributed networks, has attracted increasing attention among research communities. However, most existing models cannot be directly applied to the data with limited labeled instances (\textiti.e., the few-shot scenario). Few-shot node classification on attributed networks is gradually becoming a research hotspot. Although several methods aim to integrate meta-learning with graph neural networks to address this problem, some limitations remain. First, they all assume node representation learning using graph neural networks in homophilic graphs. %Hence, suboptimal performance is obtained when these models are applied to heterophilic graphs. Second, existing models based on meta-learning entirely depend on instance-based statistics. %which in few-shot settings are unavoidably degraded by data noise or outliers. Third, most previous models treat all sampled tasks equally and fail to adapt their uniqueness. %which has a significant impact on the overall performance of the model. To solve the above three limitations, we propose a novel graph Meta -learning framework called G raph learning based on P rototype and S caling & shifting transformation (Meta-GPS ). More specifically, we introduce an efficient method for learning expressive node representations even on heterophilic graphs and propose utilizing a prototype-based approach to initialize parameters in meta-learning. Moreover, we also leverage S$^2$ (scaling & shifting) transformation to learn effective transferable knowledge from diverse tasks. Extensive experimental results on six real-world datasets demonstrate the superiority of our proposed framework, which outperforms other state-of-the-art baselines by up to 13% absolute improvement in terms of related metrics.


9.

论文题目

Deployable and Continuable Meta-learning-Based Recommender System with Fast User-Incremental Updates

论文作者

Renchu Guan, Haoyu Pang, Fausto Giunchiglia, Ximing Li, Xuefeng Yang, Xiaoyue Feng

论文关键字

Recommender system; Cold-start problem; Meta-learning; Incremental training

SIGIR 2022

代码链接

论文摘要

User cold-start is a major challenge in building personalized recommender systems. Due to the lack of sufficient interactions, it is difficult to effectively model new users. One of the main solutions is to obtain an initial model through meta-learning (mainly gradient-based methods) and adapt it to new users with a few steps of gradient descent. Although these methods have achieved remarkable performance, they are still far from being usable in real-world applications due to their high-demand data processing, heavy computational burden, and inability to perform effective user-incremental update. In this paper, we propose a d eployable and c ontinuable m eta-learning-based r ecommendation (DCMR) approach, which can achieve fast user-incremental updating with task replay and first-order gradient descent. Specifically, we introduce a dual-constrained task sampler, distillation-based loss functions, and an adaptive controller in this framework to balance the trade-off between stability and plasticity in updating. In summary, DCMR can be updated while serving new users; in other words, it learns continuously and rapidly from a sequential user stream and is able to make recommendations at any time. The extensive experiments conducted on three benchmark datasets illustrate the superiority of our model.


10.

论文题目

Outlier-Concerned Data Completion Exploiting Intra- and Inter-Data Correlations in Sparse CrowdSensing

论文作者

En Wang; Mijia Zhang; Wenbin Liu; Haoyi Xiong; Bo Yang; Yongjian Yang; Jie Wu

论文关键字

Sparse mobile crowdsensing, matrix completion,intra- and inter-data correlation, outlier.

IEEE/ACM Transactions on Networking

代码链接

论文摘要

Mobile CrowdSensing (MCS) is a popular data collection paradigm which usually faces the problem of sparse sensed data because of the limited sensing cost. In order to address the situation of sparse data, sparse MCS recruits users to sense important areas and infers completed data by data completion, which is crucial in sparse MCS for urban sensing applications (e.g. enhancing data expression, improving urban analysis, guiding city planning, etc.) To achieve accurate completion results, previous methods usually utilize the universal similarity and conventional tendency while incorporating only a single dataset to infer the full map. However, in real-world scenarios, there may exist many kinds of data (inter-data), that could help to complement each other. Moreover, for each kind of data (intra-data), there usually exist a few but important outliers caused by the special events (e.g., parking peak, traffic congestion, or festival parade), which may behave in a different way as the statistical patterns. These outliers cannot be ignored, while it is difficult to detect and recover them in data completion because of the following challenges: 1) the infrequency and unpredictability of outliers’ occurrence, 2) the large deviations against the means compared to normal values, and 3) the complex spatiotemporal relations among inter-data. To this end, focusing on spatiotemporal data with both intra- and inter-data correlations, we propose a matrix completion method that takes outliers’ effects into consideration and exploits both intra- and inter-data correlations for enhancing performance. Specifically, we first conduct the Deep Matrix Factorization (DMF) with multiple auxiliary Neural Networks, which named Stacked Deep Matrix Factorization (SDMF). Note that the loss function of SDMF is no longer the previous MSE loss function, but replaced with an Outlier Value Loss (OVL) function to effectively detect and recover the outliers. Moreover, a spatiotemporal outlier value memory network is added for further enhancing the outlier inference. Finally, we take extensive qualitative and quantitative experiments on two popular datasets each with two types of sensing data, and the experimental results indicate the advantages of our method that outperforms the state-of-the-art methods.


11.

论文题目

Assessing the Spatiotemporal Malaria Transmission Intensity with Heterogeneous Risk Factors: A Modeling Study

论文作者

Mutong Liu,Yang Liu,Ly Po,Shang Xia,Huy Rekol,Xiao-Nong Zhou,Jiming Liu

论文关键字

Spatiotemporal Malaria Transmission Intensity, Heterogeneous Risk Factors, Modeling Study

SSRN 2022

代码链接

论文摘要

Background: Malaria control can significantly benefit from a holistic and precise way of quantitatively measuring the transmission intensity, which needs to incorporate spatiotemporally varying risk factors.

Methods: We conduct a systematic study to characterize malaria transmission intensity by taking a spatiotemporal network perspective, where nodes capture the local transmission intensities resulting from dominant vector species, the population density, and land cover, and edges describe the cross-region human mobility patterns. The inferred network enables us to obtain a comprehensive indicator for accurately assessing the transmission intensity from available empirical observation data.

Findings: Our study focuses on malaria-severe districts in Cambodia. The malaria transmission intensities determined using our indicator reveal both qualitatively and quantitatively their seasonal and geographical characteristics: the risks increase in the rainy season and decrease in the dry season; and remote and sparsely populated areas generally have higher transmission intensities than other locations. Furthermore, the spatiotemporal transmission maps show that at the beginning/end of the dry and rainy seasons, the effects of imported and exported malaria are greater than those in the middle of both seasons.

Interpretation: Human mobility (e.g., in planting/harvest seasons), environment (e.g., temperature), and contact risk (coexistences of human and vector occurrence) contribute to malaria transmission in spatiotemporally varying degrees. Quantitative relationships between the influential factors and the resulting malaria transmission risk can inform evidence-based tailor-made responses at the right locations and times.

Funding Information: This research was funded by the Ministry of Science and Technology of China (2021ZD0112501/2021ZD0112502) and the HKSAR Research Grants Council (12201318/12201619/12202220).

Declaration of Interests: We declare no competing interests.


12.

论文题目

Pyramid Tokens-to-Token Vision Transformer for Thyroid Pathology Image Classification

论文作者

Peng Yin; Bo Yu; Chengwei Jiang; Hechang Chen

论文主题词

Whole slide image, multiple instance learning,thyroid cancer, transformer, attention, image pyramid

IPTA 2022

代码链接

论文摘要

Histopathological image contains rich phenotypic information, which is beneficial to classifying tumor subtypes and predicting the development of diseases. The vast size of pathological slides makes it impossible to directly train whole slide images (WSI) on convolutional neural networks (CNNs). Most of the previous weakly supervision works divide high-resolution WSIs into small image patches and separately input them into the CNN to classify them as tumors or normal areas. The first difficulty is that although the method based on the CNN framework achieves a high accuracy rate, it increases the model parameters and computational complexity. The second difficulty is balancing the relationship between accuracy and model compu-tation. It makes the model maintain and improve the classification accuracy as much as possible based on the lightweight. In this paper, we propose a new lightweight architecture called Pyramid Tokens-to-Token VIsion Transformer (PyT2T-ViT) with multiple instance learning based on Vision Transformer. We introduce the feature extractor of the model with Token-to-Token ViT (T2T-ViT) to reduce the model parameters. The performance of the model is improved by combining the image pyramid of multiple receptive fields so that it can take into account the local and global features of the cell structure at a single scale. We applied the method to our collection of 560 thyroid pathology images from the same institution, model parameters and computation were greatly reduced. The classification effect is significantly better than the CNN-based method.


13.

论文题目

A Dual-system Method for Intelligent Fault Localization in Communication Networks

论文作者

Jinglong Ji; Fujin Zhu; Jiaxu Cui; Haihong Zhao; Bo Yang

论文主题词

communication network, fault localization, neural networks, intuitive, logical

ICC 2022 – IEEE International Conference on Communications

代码链接

论文摘要

Fault localization, as a crucial process in network fault management, is the process of deducing the exact source of a failure from a sequence of observed symptoms. Existing methods for this task are either expert system-based or data-driven. However, as communication networks grow and become more complex, conventional expert system-based approaches face problems of inefficiency and inflexibility. Besides, purely data-driven machine learning algorithms are not widely accepted in the industry because of their demand for large training sets and lack of explainability. Inspired by the dual process theory in psychology, we propose a dual-system method, named DualSys, for fault localization in this paper. In the proposed method, a fast data-driven intuitive system and a slow knowledge-driven logical system cooperate sequentially to fulfill the task. To avoid possible conflicts between the two systems, we further propose two conflict-easing mechanisms and incorporate them into the overall process. We validate our method using data from a real-world communication network. Experiment results indicate that our proposed method can get the same accuracy and explainability as knowledge-based approaches and achieve higher efficiency. As a result, we argue that our method provides network operators with a promising choice for efficient fault localization.


14.

论文题目

WHO IS YOUR RIGHT MIXUP PARTNER IN POSITIVE AND UNLABELED LEARNING

论文作者

Changchun Li, Ximing Li, Lei Feng, Jihong Ouyang

论文主题词

Positive and Unlabeled Learning, Mixup, Heuristic

ICLR

论文摘要

Positive and Unlabeled (PU) learning targets inducing a binary classifier from weak training datasets of positive and unlabeled instances, which arise in many real-world applications. In this paper, we propose a novel PU learning method, namely Positive and unlabeled learning with Partially Positive Mixup (P3Mix), which simultaneously benefits from data augmentation and supervision correction with a heuristic mixup technique. To be specific, we take inspiration from the directional boundary deviation phenomenon observed in our preliminary experiments, where the learned PU boundary tends to deviate from the fully supervised boundary towards the positive side. For the unlabeled instances with ambiguous predictive results, we select their mixup partners from the positive instances around the learned PU boundary, so as to transform them into augmented instances near to the boundary yet with more precise supervision. Accordingly, those augmented instances may push the learned PU boundary towards the fully supervised boundary, thereby improving the classification performance. Comprehensive experimental results demonstrate the effectiveness of the heuristic mixup technique in PU learning and show that P3Mix can consistently outperform the state-of-the-art PU learning methods.


15.

论文题目

Knowledge-based Temporal Fusion Network for Interpretable Online Video Popularity Prediction

论文作者

Shisong Tang, Qing Li, Xiaoteng Ma, Ci Gao, Dingmin Wang, Yong Jiang, Qian Ma, Aoyang Zhang, Hechang Chen

论文主题词:

Video popularity prediction, Knowledge graph, Attention model,Graph neural networks

WWW

代码链接

论文摘要

Predicting the popularity of online videos has many real-world applications, such as recommendation, precise advertising, and edge caching strategies. Despite many efforts have been dedicated to the online video popularity prediction, there still exist several challenges: (1) The meta-data from online videos is usually sparse and noisy, which makes it difficult to learn a stable and robust representation. (2) The influence of content features and temporal features in different life cycles of online videos is dynamically changing, so it is necessary to build a model that can capture the dynamics. (3) Besides, there is a great need to interpret the predictive behavior of the model to assist administrators of video platforms in the subsequent decision-making.

In this paper, we propose a Knowledge-based Temporal Fusion Network (KTFN) that incorporates knowledge graph representation to address the aforementioned challenges in the task of online video popularity prediction. To be more specific, we design a Tree Attention Network (TAN) to learn the embedding of online video entities in knowledge graphs via selectively aggregating local neighborhood information, thus enabling our model to learn the importance of different entities under the same relation. Besides, an Attention-based Long Short-Term Memory (ALSTM) is utilized to learn the temporal feature representation. Finally, we propose an Adaptively Temporal Feature Fusion (ATFF) scheme to adaptively fuse content features and temporal features, in which a learnable exponential decay function with the global attention mechanism is constructed. We collect two large-scale real-world datasets from the server logs of two popular Chinese online video platforms, and experimental results on the two datasets have demonstrated the superiority and interpretability of KTFN.


16.

论文题目

BO-Aug: learning data augmentation policies via Bayesian optimization

论文作者

Chunxu Zhang,Ximing Li,Zijian Zhang,Jiaxu Cui &Bo Yang

论文主题词:

Data augmentation · Bayesian optimization · Neural network

Applied Intelligence.

论文摘要

Data augmentation has been an essential technique to increase the amount and diversity of datasets, thus improving deep learning models. To pursue further performance, several automated data augmentation approaches have recently been proposed to find data augmentation policies automatically. However, there are still some key issues that deserve further exploration, i.e., a precise policy search space definition, the instructive policy evaluation method, and the low computational cost of policy search. In this paper, we propose a novel method named BO-Aug that attempts to solve the above issues. Empirical verification on three widely used image classification datasets shows that the proposed method can achieve state-of-the-art or comparable performance compared with advanced automated data augmentation methods, with a relatively low cost.


17.

论文题目

Spatiotemporal Urban Inference and Prediction in Sparse Mobile CrowdSensing: a Graph Neural Network Approach

论文作者

En Wang; Weiting Liu; Wenbin Liu; Yongjian Yang; Bo Yang; Jie Wu

论文主题词:

Mobile crowdsensing, matrix completion, graph convolution networks, spatiotemporal correlations

IEEE Transactions on Mobile Computing

代码链接

论文摘要

Mobile CrowdSensing (MCS) has recently become a promising data acquisition paradigm, which recruits a large number of users to collect data from the target sensing areas. Obviously, with the increase of sensing scale and the decrease of sensing granularity, traditional MCS cannot fully cover the required sensing areas especially the inaccessible areas. As a variant, Sparse MCS can utilize the spatiotemporal correlations in sensing data to infer the whole sensing map only by sensing a few subareas. However, in many real-world scenarios, such as traffic congestion prediction or parking occupancy detection, inferring the current unsensed data may not be the final goal. By comparison, it is more important to get the future information through the sparse sensed data. In this paper, we turn attention from inferring the current unsensed data to predicting the future unknown data and propose an urban inference and prediction framework in Sparse MCS. To deal with the sparse sensed data, we first present a bipartite-graph-based matrix completion algorithm with spatiotemporal constraints to accurately recover the current full map. Then, by exploiting spatiotemporal correlations based on the inferred full map, we present a Graph Convolutional Networks (GCN) with spatiotemporal attention to predict the future maps. Furthermore, we design a spatiotemporal iterative method to repeatedly update the spatiotemporal attentions and constraints, in order to connect the urban inference and prediction to improve the accuracy of the whole framework. Extensive experiments have been conducted on two types of typical urban sensing tasks with four real-world data sets, which verify the effectiveness of our proposed algorithms in improving the inference and prediction accuracy with the sparse sensed data.


18..

论文题目

A survey of sum–product networks structural learning

论文作者

Riting Xia,Yan Zhang,Xueyan Liu,Bo Yang

论文主题词

Sum-product networks, SPN structure learning, Deep neural model, Probabilistic graphical models, Tractable, Expressive efficiency

SSRN 2022

代码链接

论文摘要:

Sum-product networks (SPNs) in deep probabilistic models have made great progress in computer vision, robotics, neuro-symbolic artificial intelligence, natural language processing, probabilistic programming languages, and other fields. Compared with probabilistic graphical models and deep probabilistic models, SPNs can balance the tractability and expressive efficiency. In addition, SPNs remain more interpretable than deep neural models. The expressiveness and complexity of SPNs depend on its own structure. Thus, how to design an effective SPN structure learning algorithm that can balance expressiveness and complexity has become a hot research topic in recent years. In this paper, we review SPN structure learning comprehensively, including the motivation of SPN structure learning, a systematic review of related theories, the proper categorization of different SPN structure learning algorithms, several evaluation approaches and some helpful online resources. Moreover, we discuss some open issues and research directions for SPN structure learning. To our knowledge, this is the first survey to focus specifically on SPN structure learning, and we hope to provide useful references for researchers in related fields.


二. 申请专利

三. 获奖情况