Large-Margin Multi-View Information Bottleneck

In this paper, we extend the theory of the information bottleneck (IB) to learning from examples represented by multi-view features. We formulate the problem as one of encoding a communication system with multiple senders, each of which represents one view of the data. Based on the precise component...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on pattern analysis and machine intelligence Ročník 36; číslo 8; s. 1559 - 1572
Hlavní autori: Xu, Chang, Tao, Dacheng, Xu, Chao
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Los Alamitos, CA IEEE Computer Society 01.08.2014
Predmet:
Applied sciences
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Data processing. List processing. Character string processing
Exact sciences and technology
Information theory
Information, signal and communications theory
Memory organisation. Data processing
Software
Telecommunications and information theory
Bottleneck
Code distance
Generalization
Modeling
Information source
Multiplicity
information bottleneck
Vector support machine
Robustness
Alternating direction method
Complexity class
large-margin learning
Bounded error
Error bound
Distributed system
Computational complexity
Annotation
Consensus
Multi-view learning
Multiple view
Experimental result
Discrimination
Supervised learning
Objective function
Information theory
ISSN:0162-8828, 1939-3539, 1939-3539
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper, we extend the theory of the information bottleneck (IB) to learning from examples represented by multi-view features. We formulate the problem as one of encoding a communication system with multiple senders, each of which represents one view of the data. Based on the precise components filtered out from multiple information sources through a "bottleneck", a margin maximization approach is then used to strengthen the discrimination of the encoder by improving the code distance within the frame of coding theory. The resulting algorithm therefore inherits all the merits of the IB principle and coding theory. It has two distinct advantages over existing algorithms, namely, that our method finds a tradeoff between the accuracy and complexity of the multi-view model, and that the encoded multi-view data retains sufficient discrimination for classification. We also derive the robustness and generalization error bound of the proposed algorithm, and reveal the specific properties of multi-view learning. First, the complementarity of multi-view features guarantees the robustness of the algorithm. Second, the consensus of multi-view features reduces the empirical Rademacher complexity of the objective function, enhances the accuracy of the solution, and improves the generalization error bound of the algorithm. The resulting objective function is solved efficiently using the alternating direction method. Experimental results on annotation, classification and recognition tasks demonstrate that the proposed algorithm is promising for practical applications.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0162-8828
1939-3539
1939-3539
DOI:10.1109/TPAMI.2013.2296528