scholarly journals Modelling the Latent Semantics of Diffusion Sources in Information Cascade Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Ningbo Huang ◽  
Gang Zhou ◽  
Mengli Zhang ◽  
Meng Zhang ◽  
Ze Yu
Keyword(s):  
Prediction Models ◽  
Special Role ◽  
Information Cascade ◽  
Information Item ◽  
Diffusion Pattern ◽  
Adversarial Training ◽  
Common Interests ◽  
Diffusion Source ◽  
Real World Datasets ◽  
And Diffusion

Predicting the information spread tendency can help products recommendation and public opinion management. The existing information cascade prediction models are devoted to extract the chronological features from diffusion sequences but treat the diffusion sources as ordinary users. Diffusion source, the first user in the information cascade, can indicate the latent topic and diffusion pattern of an information item to mine user potential common interests, which facilitates information cascade prediction. In this paper, for modelling the abundant implicit semantics of diffusion sources in information cascade prediction, we propose a Diffusion Source latent Semantics-Fused cascade prediction framework, named DSSF. Specifically, we firstly apply diffusion sources embedding to model the special role of the source users. To learn the latent interaction between users and diffusion sources, we proposed a co-attention-based fusion gate which fuses the diffusion sources’ latent semantics with user embedding. To address the challenge that the distribution of diffusion sources is long-tailed, we develop an adversarial training framework to transfer the semantics knowledge from head to tail sources. Finally, we conduct experiments on real-world datasets, and the results show that modelling the diffusion sources can significantly improve the prediction performance. Besides, this improvement is limited for the cascades from tail sources, and the adversarial framework can help.

Interpretable Aspect-Aware Capsule Network for Peer Review Based Citation Count Prediction

2022 ◽  
Vol 40 (1) ◽  
pp. 1-29
Author(s):  
Siqing Li ◽  
Yaliang Li ◽  
Wayne Xin Zhao ◽  
Bolin Ding ◽  
Ji-Rong Wen
Keyword(s):  
Peer Review ◽  
Prediction Models ◽  
Citation Count ◽  
Specific Aspect ◽  
Semantic Features ◽  
Predictive Capacity ◽  
Topic Distribution ◽  
Real World Datasets ◽  
Data Signal ◽  
High Level

Citation count prediction is an important task for estimating the future impact of research papers. Most of the existing works utilize the information extracted from the paper itself. In this article, we focus on how to utilize another kind of useful data signal (i.e., peer review text) to improve both the performance and interpretability of the prediction models. Specially, we propose a novel aspect-aware capsule network for citation count prediction based on review text. It contains two major capsule layers, namely the feature capsule layer and the aspect capsule layer, with two different routing approaches, respectively. Feature capsules encode the local semantics from review sentences as the input of aspect capsule layer, whereas aspect capsules aim to capture high-level semantic features that will be served as final representations for prediction. Besides the predictive capacity, we also enhance the model interpretability with two strategies. First, we use the topic distribution of the review text to guide the learning of aspect capsules so that each aspect capsule can represent a specific aspect in the review. Then, we use the learned aspect capsules to generate readable text for explaining the predicted citation count. Extensive experiments on two real-world datasets have demonstrated the effectiveness of the proposed model in both performance and interpretability.

scholarly journals Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

2020 ◽  
Vol 34 (04) ◽  
pp. 5956-5963
Author(s):  
Xianfeng Tang ◽  
Huaxiu Yao ◽  
Yiwei Sun ◽  
Charu Aggarwal ◽  
Prasenjit Mitra ◽  
...  
Keyword(s):  
Time Series ◽  
Real World ◽  
Missing Values ◽  
Temporal Dynamics ◽  
Multivariate Time Series ◽  
Temporal Distribution ◽  
Joint Modeling ◽  
Adversarial Training ◽  
Global Patterns ◽  
Real World Datasets

Multivariate time series (MTS) forecasting is widely used in various domains, such as meteorology and traffic. Due to limitations on data collection, transmission, and storage, real-world MTS data usually contains missing values, making it infeasible to apply existing MTS forecasting models such as linear regression and recurrent neural networks. Though many efforts have been devoted to this problem, most of them solely rely on local dependencies for imputing missing values, which ignores global temporal dynamics. Local dependencies/patterns would become less useful when the missing ratio is high, or the data have consecutive missing values; while exploring global patterns can alleviate such problem. Thus, jointly modeling local and global temporal dynamics is very promising for MTS forecasting with missing values. However, work in this direction is rather limited. Therefore, we study a novel problem of MTS forecasting with missing values by jointly exploring local and global temporal dynamics. We propose a new framework øurs, which leverages memory network to explore global patterns given estimations from local perspectives. We further introduce adversarial training to enhance the modeling of global temporal distribution. Experimental results on real-world datasets show the effectiveness of øurs for MTS forecasting with missing values and its robustness under various missing ratios.

Analyzing concept complexity, knowledge ageing and diffusion pattern of Mooc

2017 ◽  
Vol 112 (1) ◽  
pp. 413-430 ◽  
Author(s):  
Shesen Guo ◽  
Ganzhou Zhang
Keyword(s):  
Diffusion Pattern ◽  
And Diffusion

Supervised Convolutional Matrix Factorization for Document Recommendation

2018 ◽  
Vol 17 (04) ◽  
pp. 1850018
Author(s):  
Huiting Liu ◽  
Chao Ling ◽  
Liangquan Yang ◽  
Peng Zhao
Keyword(s):  
Matrix Factorization ◽  
State Of The Art ◽  
Contextual Information ◽  
Auxiliary Information ◽  
Research Area ◽  
Information Item ◽  
Item Content ◽  
Real World Datasets ◽  
Content Information ◽  
Rating Information

Recently, document recommendation has become a very hot research area in online services. Since rating information is usually sparse with exploding growth of the numbers of users and items, conventional collaborative filtering-based methods degrade significantly in recommendation performance. To address this sparseness problem, auxiliary information such as item content information may be utilized. Convolution matrix factorization (ConvMF) is an appealing method, which tightly combines the rating and item content information. Although ConvMF captures contextual information of item content by utilizing convolutional neural network (CNN), the latent representation may not be effective when the rating information is very sparse. To address this problem, we generalize recent advances in supervised CNN and propose a novel recommendation model called supervised convolution matrix factorization (Super-ConvMF), which effectively combines the rating information, item content information and tag information into a unified recommendation framework. Experiments on three real-world datasets, two datasets come from MovieLens and the other one is from Amazon, show our model outperforms the state-of-the-art competitors in terms of the whole range of sparseness.

scholarly journals Study of the Penetration and Diffusion Characteristics of Inorganic Solidified Foam in Rock Fractures

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Yi Lu ◽  
Tao Wang ◽  
Qing Ye
Keyword(s):  
Effective Diffusion ◽  
Rock Fractures ◽  
Prediction Formula ◽  
Diffusion Distance ◽  
Coal Fire ◽  
Diffusion Characteristics ◽  
Diffusion Pattern ◽  
The Right ◽  
Fluid Penetration ◽  
And Diffusion

To explore the penetration and diffusion law in coal and rock fractures when inorganic solidified foam (ISF) is used to prevent coal fire, the penetration experiment was conducted; the results showed that the penetration pressure fluctuates within a certain range and decreases with the diffusion distance. In theXYplane, the diffusion pattern presents an ellipsoid shape, and the diffusion area becomes increasingly large over time; in theXZplane, the foam fluid penetration changes from dense to loose in theXdirection and it does not undergo downward penetration and diffuses via its own weight in theZdirection; in theYZplane, it is loose on the left and dense on the right. The viscosity of ISF was tested and then the time-varying formula was fitted. The formula of the effective diffusion radius for foam fluid diffusing in the fracture channel was determined theoretically. The permeability coefficient and other related parameters were calculated in terms of the penetration pressure and diffusion time of two monitoring points. At last, the prediction formula of effective diffusion distance of foam fluid was verified with the remaining seven monitoring points and all the relative error of monitoring is within 10%.

Investigating Associative Classification for Software Fault Prediction: An Experimental Perspective

2014 ◽  
Vol 24 (01) ◽  
pp. 61-90 ◽  
Author(s):  
Baojun Ma ◽  
Huaping Zhang ◽  
Guoqing Chen ◽  
Yanping Zhao ◽  
Bart Baesens
Keyword(s):  
Prediction Models ◽  
Prediction Performance ◽  
Fault Prediction ◽  
Machine Learning Techniques ◽  
Classification Methods ◽  
Associative Classification ◽  
Production Environment ◽  
Software Fault Prediction ◽  
Software Fault ◽  
Real World Datasets

It is a recurrent finding that software development is often troubled by considerable delays as well as budget overruns and several solutions have been proposed in answer to this observation, software fault prediction being a prime example. Drawing upon machine learning techniques, software fault prediction tries to identify upfront software modules that are most likely to contain faults, thereby streamlining testing efforts and improving overall software quality. When deploying fault prediction models in a production environment, both prediction performance and model comprehensibility are typically taken into consideration, although the latter is commonly overlooked in the academic literature. Many classification methods have been suggested to conduct fault prediction; yet associative classification methods remain uninvestigated in this context. This paper proposes an associative classification (AC)-based fault prediction method, building upon the CBA2 algorithm. In an empirical comparison on 12 real-world datasets, the AC-based classifier is shown to achieve a predictive performance competitive to those of models induced by five other tree/rule-based classification techniques. In addition, our findings also highlight the comprehensibility of the AC-based models, while achieving similar prediction performance. Furthermore, the possibilities of cross project prediction are investigated, strengthening earlier findings on the feasibility of such approach when insufficient data on the target project is available.

scholarly journals Radiological evaluation of deep soft tissue fibromatosis, the characteristic MR criteria on conventional and corresponding diffusion-weighted images

2020 ◽  
Vol 51 (1) ◽  
Author(s):  
Rania Zeitoun ◽  
Sarah Maged Khafagy ◽  
Ikram Hamed Mahmoud ◽  
Nagui Mohamed Abd El-Wahab
Keyword(s):  
Mr Images ◽  
Post Contrast ◽  
Diffusion Weighted Images ◽  
Diffusion Weighted ◽  
Local Staging ◽  
Diffusion Pattern ◽  
Adc Values ◽  
Characteristic Features ◽  
And Diffusion ◽  
Deep Fibromatosis

Abstract Background To analyze the characteristic features of deep fibromatosis on conventional and diffusion-weighted MR images. Result The lesions were growing along the musculoaponeurotic fascia, mostly invaded the muscles, and showed ill-defined margins, low T2 signal bands and areas, and facial tail sign. Diffusion images showed mostly high or high mixed with low signal; only 2 lesions showed a persistent low signal. The average mean and minimum ADC values were 1.41 ± 0.26 × 10−3 mm2/s and 0.79 ± 0.43 × 10−3 mm2/s respectively. Post-contrast and DWI detected synchronous lesions and extensions missed on T1 and T2 images. Conclusion The most frequent MR features of deep fibromatosis are low T2 signal bands and areas, fascial tail sign, ill or partially defined margins, and predominant restricted diffusion pattern in addition to areas of “T2-blackout effect.” Post-contrast and DWI are more valuable in local staging of the tumor.

Numerical Simulation of Diffusion of UDMH in Confined Space

2013 ◽  
Vol 295-298 ◽  
pp. 586-589
Author(s):  
Jia Zhao Chen ◽  
Chao Ning ◽  
Yu Xiang Zhang
Keyword(s):  
Numerical Simulation ◽  
Concentration Distribution ◽  
Geometric Model ◽  
Polluted Area ◽  
Confined Space ◽  
Gas Concentration ◽  
Diffusion Pattern ◽  
Toxic Gas ◽  
3D Geometric Model ◽  
And Diffusion

In order to study the diffusion pattern of Unsymmetrical Dimethyl Hydrazine (UDMH) in a confined space, a 3D geometric model of cylindrical space with a column obstacle in the center was built and diffusion of UDMH in the space was simulated by using FLUENT. The gas concentration distribution in the space was gained at different moments, and the polluted area with concentration above 0.5ppm was focused on. The simulation result suggests that the toxic gas is mainly concentrated in an area about 1m above the bottom of the space, and ventilation can effectively reduce the hazard time and continuous expansion of polluted area.

Sign in / Sign up

Export Citation Format

Share Document