A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection

He, Hongmei; Watson, Tim; Maple, Carsten; Mehnen, Jörn; Tiwari, Ashutosh

doi:10.1109/ijcnn.2017.7966343

Cited by 19 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed attentive federated aggregation can also add this mechanism smoothly using Equation 6. The randomization is added in before the clients send the updated parameters to the server, but it is written in the form of server optimization for simplicity.…”

Section: Differential Privacymentioning

confidence: 99%

“…Distributed intelligent agents take a shared global model from the central server's parameters as initialization to train their own private models using personal data, and make predictions on their own physical devices. There are many applications of federated learning in the real world, for example, predicting the most likely photos a mobile user would like to share on the social websites [4], predicting the next word for mobile keyboards [5], retrieving the most important notifications, and detecting the spam messages [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Private Neural Language Modeling with Attentive Aggregation

Pan

Long

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

113

View full text Add to dashboard Cite

Mobile keyboard suggestion is typically regarded as a word-level language modeling problem. Centralized machine learning techniques require the collection of massive user data for training purposes, which may raise privacy concerns in relation to users' sensitive data. Federated learning (FL) provides a promising approach to learning private language modeling for intelligent personalized keyboard suggestions by training models on distributed clients rather than training them on a central server. To obtain a global model for prediction, existing FL algorithms simply average the client models and ignore the importance of each client during model aggregation. Furthermore, there is no optimization for learning a well-generalized global model on the central server. To solve these problems, we propose a novel model aggregation with an attention mechanism considering the contribution of client models to the global model, together with an optimization technique during server aggregation. Our proposed attentive aggregation method minimizes the weighted distance between the server model and client models by iteratively updating parameters while attending to the distance between the server model and client models. Experiments on two popular language modeling datasets and a social media dataset show that our proposed method outperforms its counterparts in terms of perplexity and communication cost in most settings of comparison.

show abstract

Section: Differential Privacymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning Private Neural Language Modeling with Attentive Aggregation

Pan

Long

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

113

View full text Add to dashboard Cite

show abstract

“…The SMSSpamCollection database [15], has 5574 raw messages, including 747 spams. He et al [13] extracted 20 features from the database, and the number of features was reduced to 14 by combining some features with similar meanings [19]. We use the 14 attribute database for the experiments.…”

Section: Case Study On the Smsspamcollection Databasementioning

confidence: 99%

How Good a Shallow Neural Network Is for Solving Non-linear Decision Making Problems

Zhu

et al. 2018

Advances in Brain Inspired Cognitive Systems

Self Cite

View full text Add to dashboard Cite

The universe approximate theorem states that a shadow neural network (one hidden layer) can represent any non-linear function. In this paper, we aim at examining how good a shadow neural network is for solving non-linear decision making problems. We proposed a performance driven incremental approach to searching the best shadow neural network for decision making, given a data set. The experimental results on the two benchmark data sets, Breast Cancer in Wisconsin and SMS Spams, demonstrate the correction of universe approximate theorem, and show that the number of hidden neurons, taking about the half of input number, is good enough to represent the function from data. It is shown that the performance driven BP learning is faster than the error-driven BP learning, and that the performance of the SNN obtained by the former is not worse than that of the SNN obtained by the latter. This indicates that when learning a neural network with the BP algorithm, the performance reaches a certain value quickly, but the error may still keep reducing. The performance of the SNNs for the two databases is comparable to or better than that of the optimal linguistic attribute hierarchy, obtained by a genetic algorithm in wrapper or in terms of semantics manually, which is much time-consuming.

show abstract

“…26 Recent work in this area has also examined that the exploitation of the constantly growing semantic attributes can be efficiently utilized in pedestrian re-identification to bridge the so-called "semantic gap" between extractable low-level feature representations and high-level semantic understanding of the visual objects and improve the accuracy of the recognition when the semantic attributes are constructed to a proper hierarchy. 27 Remarkably, Wang et al and Ye et al gave a way employing attributes to deal with person re-identification problem. 28,29 The learning and usage of semantic attribute representations benefit for visual recognition.…”

Section: Attribute-based Modelingmentioning

confidence: 99%

Data‐driven pedestrian re‐identification based on hierarchical semantic representation

Cheng

Tao

et al. 2017

Concurrency and Computation

View full text Add to dashboard Cite

Summary Limited number of labeled data of surveillance video causes the training of supervised model for pedestrian re‐identification to be a difficult task. Besides, applications of pedestrian re‐identification in pedestrian retrieving and criminal tracking are limited because of the lack of semantic representation. In this paper, a data‐driven pedestrian re‐identification model based on hierarchical semantic representation is proposed, extracting essential features with unsupervised deep learning model and enhancing the semantic representation of features with hierarchical mid‐level ‘attributes’. Firstly, CNNs, well‐trained with the training process of CAEs, is used to extract features of horizontal blocks segmented from unlabeled pedestrian images. Then, these features are input into corresponding attribute classifiers to judge whether the pedestrian has the attributes. Lastly, with a table of ‘attributes‐classes mapping relations’, final result can be calculated. Under the premise of improving the accuracy of attribute classifier, our qualitative results show its clear advantages over the CHUK02, VIPeR, and i‐LIDS data set. Our proposed method is proved to effectively solve the problem of dependency on labeled data and lack of semantic expression, and it also significantly outperforms the state‐of‐the‐art in terms of accuracy and semanteme.

show abstract

A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection

Cited by 19 publications

References 9 publications

Learning Private Neural Language Modeling with Attentive Aggregation

Learning Private Neural Language Modeling with Attentive Aggregation

How Good a Shallow Neural Network Is for Solving Non-linear Decision Making Problems

Data‐driven pedestrian re‐identification based on hierarchical semantic representation

Contact Info

Product

Resources

About