-
Chapter and Conference Paper
Prevention of GAN-Based Privacy Inferring Attacks Towards Federated Learning
With the increasing amount of data, data privacy has drawn great concern in machine learning among the public. Federated Learning, which is a new kind of distributed learning framework, enables data providers ...
-
Chapter and Conference Paper
DynGraphGAN: Dynamic Graph Embedding via Generative Adversarial Networks
Graphs have become widely adopted as a means of representing relationships between entities in many applications. These graphs often evolve over time. Learning effective representations preserving graph topolo...
-
Chapter and Conference Paper
Rules for Inducing Hierarchies from Social Tagging Data
Automatic generation of hierarchies from social tags is a challenging task. We identified three rules, set inclusion, graph centrality and information-theoretic condition from the literature and proposed two n...
-
Chapter and Conference Paper
Randomizing SVM Against Adversarial Attacks Under Uncertainty
Robust machine learning algorithms have been widely studied in adversarial environments where the adversary maliciously manipulates data samples to evade security systems. In this paper, we propose randomized ...
-
Chapter and Conference Paper
A CRF-Based Stacking Model with Meta-features for Named Entity Recognition
Named Entity Recognition (NER) is a challenging task in Natural Language Processing. Recently, machine learning based methods are widely used for the NER task and outperform traditional handcrafted rule based ...
-
Chapter and Conference Paper
High Capacity Reversible Data Hiding with Contrast Enhancement
Reversible data hiding aims at recovering exactly the cover image from the marked image after extracting the hidden data. Reversible data hiding with contrast enhancement proposed by Wu et al. achieved a good eff...
-
Chapter and Conference Paper
PreNet: Parallel Recurrent Neural Networks for Image Classification
Convolutional Neural Networks (CNNs) have made outstanding achievements in computer vision, e.g., image classification and object detection, by modelling the receptive field of visual cortex with convolution a...
-
Chapter and Conference Paper
Relevance and Coherence Based Image Caption
The attention-based image caption framework has been widely explored in recent years. However, most techniques generate next word conditioned on previous words and current visual contents, while the relationsh...
-
Chapter and Conference Paper
Image Forgery Detection Based on Semantic Image Understanding
Image forensics has been focusing on low-level visual features, paying little attention to high-level semantic information of the image. In this work, we propose the framework for image forgery detection based...
-
Chapter and Conference Paper
Incremental Hierarchical Clustering of Stochastic Pattern-Based Symbolic Data
Classic data analysis techniques generally assume that variables have single values only. However, the data complexity during the age of big data has gone beyond the classic framework such that variable values...
-
Chapter and Conference Paper
General Purpose Index-Based Method for Efficient MaxRS Query
The Maximizing Range Sum problem is widely applied in facility locating, spatial data mining, and clustering problems. The current most efficient method solves it in time
-
Chapter and Conference Paper
Cross-Modal Search on Social Networking Systems by Exploring Wikipedia Concepts
The increasing popularity of social networking systems (SNSs) has created large quantities of data from multiple modalities such as text and image. Retrieval of data, however, is constrained to a specific moda...
-
Chapter and Conference Paper
Biased Respondent Group Selection Under Limited Budget for Minority Opinion Survey
This paper discusses a new approach to use the information from a special social network with high homophily to select a survey respondent group under a limited budget such that the result of the survey is bia...
-
Chapter and Conference Paper
Social Relation Based Long-Term Vaccine Distribution Planning to Suppress Pandemic
This paper introduces a new optimization problem which aims to develop a distribution plan of vaccines which will be supplied over time such that an epidemic can be best suppressed until a complete cure for it...
-
Chapter and Conference Paper
Web Knowledge Base Improved OCR Correction for Chinese Business Cards
In the field of Optical Character Recognition(OCR), improving the recognition accuracy has been extensively studied in the past decades. In this paper, different from previously published model-based correctio...
-
Chapter and Conference Paper
Shortest Path and Word Vector Based Relation Representation and Clustering
Relation representation plays an important role in text understanding. In this paper, different from previously published supervised methods or semi-supervised methods, an new method of relation representation...
-
Chapter and Conference Paper
Collecting Valuable Information from Fast Text Streams
It has become a challenging work to collect valuable information from fast text streams. In this work, we propose a method which gains useful information effectively and efficiently. Firstly, we maintain an an...
-
Chapter and Conference Paper
An Ontology-Based Domain Modeling Framework for Knowledge Service in Digital Library
In Digital Library, information is often stored in unstructured and semi-structured textual form. Domain modeling techniques are used for specific domain knowledge services in order to make use of the massive ...
-
Chapter and Conference Paper
Detecting Anomalies in Microblogging via Nonnegative Matrix Tri-Factorization
With the increasing of anomalous user’s intelligent, it is difficult to detect the anomalous users and messages in microblogging. Most of the studies attempt to detect anomalous users or messages individually ...
-
Chapter and Conference Paper
A New Similarity Measure-Based Collaborative Filtering Approach for Recommender Systems
Collaborative filtering (CF) is the most popular recommendation approach in personalization techniques but still suffers from poor recommendation accuracy. This study incorporates fuzzy set technique and user-...