• Publications
  • Influence
GAIN: Missing Data Imputation using Generative Adversarial Nets
TLDR
This work proposes a novel method for imputing missing data by adapting the well-known Generative Adversarial Nets (GAN) framework and calls it GAIN, which significantly outperforms state-of-the-art imputation methods.
DeepHit: A Deep Learning Approach to Survival Analysis With Competing Risks
TLDR
A very different approach to survival analysis, DeepHit, that uses a deep neural network to learn the distribution of survival times directly and achieves large and statistically significant performance improvements over previous state-of-the-art methods.
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
TLDR
This paper investigates a method for ensuring (differential) privacy of the generator of the Generative Adversarial Nets (GAN) framework, and modifies the Private Aggregation of Teacher Ensembles (PATE) framework and applies it to GANs.
Time-series Generative Adversarial Networks
TLDR
A novel framework for generating realistic time-series data that combines the flexibility of the unsupervised paradigm with the control afforded by supervised training is proposed, which consistently and significantly outperforms state-of-the-art benchmarks with respect to measures of similarity and predictive ability.
The MPEG-4 fine-grained scalable video coding method for multimedia streaming over IP
TLDR
This paper describes a new scalable video-coding framework that has been adopted recently by the MPEG-4 video standard, known as Fine-Granular-Scalability (FGS), which consists of a rich set of video coding tools that support quality, temporal, and hybrid temporal-SNR scalabilities.
Bargaining Strategies for Networked Multimedia Resource Management
TLDR
This work proposes to deploy the well-known game theoretic concept of bargaining to allocate the bandwidth fairly and optimally among multiple collaborative users and considers two bargaining solutions for the resource management problem: the Nash bargaining solution (NBS) and the Kalai-Smorodinsky bargaining Solution (KSBS).
Reputation-based incentive protocols in crowdsourcing applications
TLDR
It is proved that the proposed incentives protocol can make the website operate close to Pareto efficiency, and also examines an alternative scenario, where the protocol designer aims at maximizing the revenue of the website and evaluate the performance of the optimal protocol.
Adaptive cross-layer protection strategies for robust scalable video transmission over 802.11 WLANs
TLDR
This paper evaluates different error control and adaptation mechanisms available in the different layers for robust transmission of video, namely MAC retransmission strategy, application-layer forward error correction, bandwidth-adaptive compression using scalable coding, and adaptive packetization strategies, and proposes a novel adaptive cross-layer protection strategy.
Online Learning in Large-Scale Contextual Recommender Systems
TLDR
A novel large-scale, context-aware recommender system that provides accurate recommendations, scalability to a large number of diverse users and items, differential services, and does not suffer from “cold start” problems is proposed.
...
...