learning framework
Recently Published Documents





2022 ◽  
Vol 22 (3) ◽  
pp. 1-24
Yizhang Jiang ◽  
Xiaoqing Gu ◽  
Lei Hua ◽  
Kang Li ◽  
Yuwen Tao ◽  

Artificial intelligence– (AI) based fog/edge computing has become a promising paradigm for infectious disease. Various AI algorithms are embedded in cooperative fog/edge devices to construct medical Internet of Things environments, infectious disease forecast systems, smart health, and so on. However, these systems are usually done in isolation, which is called single-task learning. They do not consider the correlation and relationship between multiple/different tasks, so some common information in the model parameters or data characteristics is lost. In this study, each data center in fog/edge computing is considered as a task in the multi-task learning framework. In such a learning framework, a multi-task weighted Takagi-Sugeno-Kang (TSK) fuzzy system, called MW-TSKFS, is developed to forecast the trend of Coronavirus disease 2019 (COVID-19). MW-TSKFS provides a multi-task learning strategy for both antecedent and consequent parameters of fuzzy rules. First, a multi-task weighted fuzzy c-means clustering algorithm is developed for antecedent parameter learning, which extracts the public information among all tasks and the private information of each task. By sharing the public cluster centroid and public membership matrix, the differences of commonality and individuality can be further exploited. For consequent parameter learning of MW-TSKFS, a multi-task collaborative learning mechanism is developed based on ε-insensitive criterion and L2 norm penalty term, which can enhance the generalization and forecasting ability of the proposed fuzzy system. The experimental results on the real COVID-19 time series show that the forecasting tend model based on multi-task the weighted TSK fuzzy system has a high application value.

2022 ◽  
Vol 40 (3) ◽  
pp. 1-29
Peijie Sun ◽  
Le Wu ◽  
Kun Zhang ◽  
Yu Su ◽  
Meng Wang

Review based recommendation utilizes both users’ rating records and the associated reviews for recommendation. Recently, with the rapid demand for explanations of recommendation results, reviews are used to train the encoder–decoder models for explanation text generation. As most of the reviews are general text without detailed evaluation, some researchers leveraged auxiliary information of users or items to enrich the generated explanation text. Nevertheless, the auxiliary data is not available in most scenarios and may suffer from data privacy problems. In this article, we argue that the reviews contain abundant semantic information to express the users’ feelings for various aspects of items, while these information are not fully explored in current explanation text generation task. To this end, we study how to generate more fine-grained explanation text in review based recommendation without any auxiliary data. Though the idea is simple, it is non-trivial since the aspect is hidden and unlabeled. Besides, it is also very challenging to inject aspect information for generating explanation text with noisy review input. To solve these challenges, we first leverage an advanced unsupervised neural aspect extraction model to learn the aspect-aware representation of each review sentence. Thus, users and items can be represented in the aspect space based on their historical associated reviews. After that, we detail how to better predict ratings and generate explanation text with the user and item representations in the aspect space. We further dynamically assign review sentences which contain larger proportion of aspect words with larger weights to control the text generation process, and jointly optimize rating prediction accuracy and explanation text generation quality with a multi-task learning framework. Finally, extensive experimental results on three real-world datasets demonstrate the superiority of our proposed model for both recommendation accuracy and explainability.

2022 ◽  
Vol 40 (3) ◽  
pp. 1-28
Surong Yan ◽  
Kwei-Jay Lin ◽  
Xiaolin Zheng ◽  
Haosen Wang

Explicit and implicit knowledge about users and items have been used to describe complex and heterogeneous side information for recommender systems (RSs). Many existing methods use knowledge graph embedding (KGE) to learn the representation of a user-item knowledge graph (KG) in low-dimensional space. In this article, we propose a lightweight end-to-end joint learning framework for fusing the tasks of KGE and RSs at the model level. Our method proposes a lightweight KG embedding method by using bidirectional bijection relation-type modeling to enable scalability for large graphs while using self-adaptive negative sampling to optimize negative sample generating. Our method further generates the integrated views for users and items based on relation-types to explicitly model users’ preferences and items’ features, respectively. Finally, we add virtual “recommendation” relations between the integrated views of users and items to model the preferences of users on items, seamlessly integrating RS with user-item KG over a unified graph. Experimental results on multiple datasets and benchmarks show that our method can achieve a better accuracy of recommendation compared with existing state-of-the-art methods. Complexity and runtime analysis suggests that our method can gain a lower time and space complexity than most of existing methods and improve scalability.

2022 ◽  
Vol 13 (2) ◽  
pp. 1-19
Yingxue Zhang ◽  
Yanhua Li ◽  
Xun Zhou ◽  
Jun Luo ◽  
Zhi-Li Zhang

Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quickly adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.

2022 ◽  
Vol 122 ◽  
pp. 108345
Md Geaur Rahman ◽  
Md Zahidul Islam

2022 ◽  
Vol 389 ◽  
pp. 114424
Hengjie Wang ◽  
Robert Planas ◽  
Aparna Chandramowlishwaran ◽  
Ramin Bostanabad

2022 ◽  
Vol 187 ◽  
pp. 108499
Andong Li ◽  
Chengshi Zheng ◽  
Lu Zhang ◽  
Xiaodong Li

Sign in / Sign up

Export Citation Format

Share Document