Budgeted online influence maximization
Document type :
Communication dans un congrès avec actes
Title :
Budgeted online influence maximization
Author(s) :
Perrault, Pierre [Auteur]
Ecole Normale Supérieure Paris-Saclay [ENS Paris Saclay]
Sequential Learning [SEQUEL]
Adobe Research
Scool [Scool]
Healey, Jennifer [Auteur]
Adobe Research
Wen, Zheng [Auteur]
DeepMind [London]
Valko, Michal [Auteur]
DeepMind [London]
Ecole Normale Supérieure Paris-Saclay [ENS Paris Saclay]
Sequential Learning [SEQUEL]
Adobe Research
Scool [Scool]
Healey, Jennifer [Auteur]
Adobe Research
Wen, Zheng [Auteur]
DeepMind [London]
Valko, Michal [Auteur]
DeepMind [London]
Conference title :
International Conference on Machine Learning
City :
Vienna
Country :
Autriche
Start date of the conference :
2020
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
We introduce a new budgeted framework for on-line influence maximization, considering the total cost of an advertising campaign instead of the common cardinality constraint on a chosen influ-encer set. Our approach models ...
Show more >We introduce a new budgeted framework for on-line influence maximization, considering the total cost of an advertising campaign instead of the common cardinality constraint on a chosen influ-encer set. Our approach models better the real-world setting where the cost of influencers varies and advertizers want to find the best value for their overall social advertising budget. We propose an algorithm assuming an independent cascade diffusion model and edge-level semi-bandit feedback, and provide both theoretical and experimental results. Our analysis is also valid for the cardinality-constraint setting and improves the state of the art regret bound in this case.Show less >
Show more >We introduce a new budgeted framework for on-line influence maximization, considering the total cost of an advertising campaign instead of the common cardinality constraint on a chosen influ-encer set. Our approach models better the real-world setting where the cost of influencers varies and advertizers want to find the best value for their overall social advertising budget. We propose an algorithm assuming an independent cascade diffusion model and edge-level semi-bandit feedback, and provide both theoretical and experimental results. Our analysis is also valid for the cardinality-constraint setting and improves the state of the art regret bound in this case.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Comment :
Virtual conference
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-02904278/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02904278/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02904278/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02904278/document
- Open access
- Access the document
- document
- Open access
- Access the document
- icml2020_boim__Version_2293_.pdf
- Open access
- Access the document