Sorry, you need to enable JavaScript to visit this website.

Emerging: Big Data

Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers


Due to the grow of modern dataset size and the desire to harness computing power of multiple machines, there is a recent surge of interest in the design of distributed machine learning algorithms. However, distributed algorithms are sensitive to Byzantine attackers who can send falsified data to prevent the convergence of algorithms or lead the algorithms to converge to value of the attackers' choice. Our novel algorithm can deal with an arbitrary number of Byzantine attackers.

Paper Details

Authors:
Lifeng Lai
Submitted On:
14 April 2018 - 12:40am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSPposter.pdf

(229 downloads)

Subscribe

[1] Lifeng Lai, "Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2795. Accessed: Jul. 19, 2018.
@article{2795-18,
url = {http://sigport.org/2795},
author = {Lifeng Lai },
publisher = {IEEE SigPort},
title = {Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers},
year = {2018} }
TY - EJOUR
T1 - Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers
AU - Lifeng Lai
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2795
ER -
Lifeng Lai. (2018). Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers. IEEE SigPort. http://sigport.org/2795
Lifeng Lai, 2018. Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers. Available at: http://sigport.org/2795.
Lifeng Lai. (2018). "Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers." Web.
1. Lifeng Lai. Robust Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2795

Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?


A novel method for common and individual feature analysis from exceedingly large-scale data is proposed, in order to ensure the tractability of both the computation and storage and thus mitigate the curse of dimensionality, a major bottleneck in modern data science. This is achieved by making use of the inherent redundancy in so-called multi-block data structures, which represent multiple observations of the same phenomenon taken at different times, angles or recording conditions.

Paper Details

Authors:
Ilia Kisil, Giuseppe G. Calvi, Andrzej Cichocki, Danilo P. Mandic
Submitted On:
13 April 2018 - 2:12pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

KISIL_ICASSP_2018.pdf

(85 downloads)

Subscribe

[1] Ilia Kisil, Giuseppe G. Calvi, Andrzej Cichocki, Danilo P. Mandic, "Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2739. Accessed: Jul. 19, 2018.
@article{2739-18,
url = {http://sigport.org/2739},
author = {Ilia Kisil; Giuseppe G. Calvi; Andrzej Cichocki; Danilo P. Mandic },
publisher = {IEEE SigPort},
title = {Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?},
year = {2018} }
TY - EJOUR
T1 - Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?
AU - Ilia Kisil; Giuseppe G. Calvi; Andrzej Cichocki; Danilo P. Mandic
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2739
ER -
Ilia Kisil, Giuseppe G. Calvi, Andrzej Cichocki, Danilo P. Mandic. (2018). Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?. IEEE SigPort. http://sigport.org/2739
Ilia Kisil, Giuseppe G. Calvi, Andrzej Cichocki, Danilo P. Mandic, 2018. Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?. Available at: http://sigport.org/2739.
Ilia Kisil, Giuseppe G. Calvi, Andrzej Cichocki, Danilo P. Mandic. (2018). "Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality?." Web.
1. Ilia Kisil, Giuseppe G. Calvi, Andrzej Cichocki, Danilo P. Mandic. Common and Individual Feature Extraction using Tensor Decompositions: A Remedy for the Curse of Dimensionality? [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2739

Deep Learning for Joint Source-Channel Coding of Text


We consider the problem of joint source and channel coding of structured data such as natural language over a noisy channel. The typical approach inspired by information theory to this problem involves performing source coding to first compress the text and then channel coding to add robustness while transmitting across the channel; this approach is optimal with arbitrarily large block lengths for discrete memoryless channels.

Paper Details

Authors:
Nariman Farsad, Milind Rao, and Andrea Goldsmith
Submitted On:
13 April 2018 - 11:22am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp_jointSC_handout.pdf

(41 downloads)

Subscribe

[1] Nariman Farsad, Milind Rao, and Andrea Goldsmith, "Deep Learning for Joint Source-Channel Coding of Text", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2717. Accessed: Jul. 19, 2018.
@article{2717-18,
url = {http://sigport.org/2717},
author = {Nariman Farsad; Milind Rao; and Andrea Goldsmith },
publisher = {IEEE SigPort},
title = {Deep Learning for Joint Source-Channel Coding of Text},
year = {2018} }
TY - EJOUR
T1 - Deep Learning for Joint Source-Channel Coding of Text
AU - Nariman Farsad; Milind Rao; and Andrea Goldsmith
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2717
ER -
Nariman Farsad, Milind Rao, and Andrea Goldsmith. (2018). Deep Learning for Joint Source-Channel Coding of Text. IEEE SigPort. http://sigport.org/2717
Nariman Farsad, Milind Rao, and Andrea Goldsmith, 2018. Deep Learning for Joint Source-Channel Coding of Text. Available at: http://sigport.org/2717.
Nariman Farsad, Milind Rao, and Andrea Goldsmith. (2018). "Deep Learning for Joint Source-Channel Coding of Text." Web.
1. Nariman Farsad, Milind Rao, and Andrea Goldsmith. Deep Learning for Joint Source-Channel Coding of Text [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2717

PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION

Paper Details

Authors:
Qingming Li, Zhanjiang Chen, H. Vicky Zhao, Yan Lindsay Sun
Submitted On:
13 April 2018 - 4:51am
Short Link:
Type:
Event:

Document Files

PRIMA4.pdf

(42 downloads)

Subscribe

[1] Qingming Li, Zhanjiang Chen, H. Vicky Zhao, Yan Lindsay Sun, "PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2656. Accessed: Jul. 19, 2018.
@article{2656-18,
url = {http://sigport.org/2656},
author = {Qingming Li; Zhanjiang Chen; H. Vicky Zhao; Yan Lindsay Sun },
publisher = {IEEE SigPort},
title = {PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION},
year = {2018} }
TY - EJOUR
T1 - PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION
AU - Qingming Li; Zhanjiang Chen; H. Vicky Zhao; Yan Lindsay Sun
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2656
ER -
Qingming Li, Zhanjiang Chen, H. Vicky Zhao, Yan Lindsay Sun. (2018). PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION. IEEE SigPort. http://sigport.org/2656
Qingming Li, Zhanjiang Chen, H. Vicky Zhao, Yan Lindsay Sun, 2018. PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION. Available at: http://sigport.org/2656.
Qingming Li, Zhanjiang Chen, H. Vicky Zhao, Yan Lindsay Sun. (2018). "PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION." Web.
1. Qingming Li, Zhanjiang Chen, H. Vicky Zhao, Yan Lindsay Sun. PRIMA: PROBABILISTIC RANKING WITH INTER-ITEM COMPETITION AND MULTI-ATTRIBUTE UTILITY FUNCTION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2656

Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution


In a social network, influence maximization is the problem of identifying a set of users that own the maximum influence ability across the network. In this paper, a novel credit distribution (CD) based model, termed as the multi-action CD (mCD) model, is introduced to quantify the influence ability of each user. Compared to existing models, the new model can work with practical datasets where one type of action is recorded for multiple times. Based on this model, influence maximization is formulated as a submodular maximization problem under a knapsack constraint, which is NP-hard.

Paper Details

Authors:
Qilian Yu, Hang Li, Yun Liao, Shuguang Cui
Submitted On:
12 April 2018 - 4:47pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP Poster.pdf

(476 downloads)

Subscribe

[1] Qilian Yu, Hang Li, Yun Liao, Shuguang Cui, "Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2500. Accessed: Jul. 19, 2018.
@article{2500-18,
url = {http://sigport.org/2500},
author = {Qilian Yu; Hang Li; Yun Liao; Shuguang Cui },
publisher = {IEEE SigPort},
title = {Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution},
year = {2018} }
TY - EJOUR
T1 - Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution
AU - Qilian Yu; Hang Li; Yun Liao; Shuguang Cui
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2500
ER -
Qilian Yu, Hang Li, Yun Liao, Shuguang Cui. (2018). Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution. IEEE SigPort. http://sigport.org/2500
Qilian Yu, Hang Li, Yun Liao, Shuguang Cui, 2018. Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution. Available at: http://sigport.org/2500.
Qilian Yu, Hang Li, Yun Liao, Shuguang Cui. (2018). "Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution." Web.
1. Qilian Yu, Hang Li, Yun Liao, Shuguang Cui. Streaming Influence Maximization in Social Networks based on Multi-Action Credit Distribution [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2500

Graph learning based on total variation minimization

Paper Details

Authors:
Peter Berger, Manfred Buchacher, Gabor Hannak, Gerald Matz
Submitted On:
12 April 2018 - 1:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_Peter_Berger.pdf

(37 downloads)

Subscribe

[1] Peter Berger, Manfred Buchacher, Gabor Hannak, Gerald Matz, "Graph learning based on total variation minimization", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2446. Accessed: Jul. 19, 2018.
@article{2446-18,
url = {http://sigport.org/2446},
author = {Peter Berger; Manfred Buchacher; Gabor Hannak; Gerald Matz },
publisher = {IEEE SigPort},
title = {Graph learning based on total variation minimization},
year = {2018} }
TY - EJOUR
T1 - Graph learning based on total variation minimization
AU - Peter Berger; Manfred Buchacher; Gabor Hannak; Gerald Matz
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2446
ER -
Peter Berger, Manfred Buchacher, Gabor Hannak, Gerald Matz. (2018). Graph learning based on total variation minimization. IEEE SigPort. http://sigport.org/2446
Peter Berger, Manfred Buchacher, Gabor Hannak, Gerald Matz, 2018. Graph learning based on total variation minimization. Available at: http://sigport.org/2446.
Peter Berger, Manfred Buchacher, Gabor Hannak, Gerald Matz. (2018). "Graph learning based on total variation minimization." Web.
1. Peter Berger, Manfred Buchacher, Gabor Hannak, Gerald Matz. Graph learning based on total variation minimization [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2446

Distinguished Lecture: IOT, Data and Healthcare: How do we get it right


Abstract

DL_Wendy.pdf

PDF icon DL_Wendy.pdf (157 downloads)

Paper Details

Authors:
Wendy Nilsen
Submitted On:
16 November 2017 - 11:01am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

DL_Wendy.pdf

(157 downloads)

Subscribe

[1] Wendy Nilsen, "Distinguished Lecture: IOT, Data and Healthcare: How do we get it right", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2362. Accessed: Jul. 19, 2018.
@article{2362-17,
url = {http://sigport.org/2362},
author = {Wendy Nilsen },
publisher = {IEEE SigPort},
title = {Distinguished Lecture: IOT, Data and Healthcare: How do we get it right},
year = {2017} }
TY - EJOUR
T1 - Distinguished Lecture: IOT, Data and Healthcare: How do we get it right
AU - Wendy Nilsen
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2362
ER -
Wendy Nilsen. (2017). Distinguished Lecture: IOT, Data and Healthcare: How do we get it right. IEEE SigPort. http://sigport.org/2362
Wendy Nilsen, 2017. Distinguished Lecture: IOT, Data and Healthcare: How do we get it right. Available at: http://sigport.org/2362.
Wendy Nilsen. (2017). "Distinguished Lecture: IOT, Data and Healthcare: How do we get it right." Web.
1. Wendy Nilsen. Distinguished Lecture: IOT, Data and Healthcare: How do we get it right [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2362

SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics

Paper Details

Authors:
Rabindra K. Barik, Harishchandra Dubey, Kunal Mankodiya
Submitted On:
15 November 2017 - 9:23am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Slides_KM

(151 downloads)

Subscribe

[1] Rabindra K. Barik, Harishchandra Dubey, Kunal Mankodiya, "SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2357. Accessed: Jul. 19, 2018.
@article{2357-17,
url = {http://sigport.org/2357},
author = {Rabindra K. Barik; Harishchandra Dubey; Kunal Mankodiya },
publisher = {IEEE SigPort},
title = {SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics},
year = {2017} }
TY - EJOUR
T1 - SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics
AU - Rabindra K. Barik; Harishchandra Dubey; Kunal Mankodiya
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2357
ER -
Rabindra K. Barik, Harishchandra Dubey, Kunal Mankodiya. (2017). SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics. IEEE SigPort. http://sigport.org/2357
Rabindra K. Barik, Harishchandra Dubey, Kunal Mankodiya, 2017. SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics. Available at: http://sigport.org/2357.
Rabindra K. Barik, Harishchandra Dubey, Kunal Mankodiya. (2017). "SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics." Web.
1. Rabindra K. Barik, Harishchandra Dubey, Kunal Mankodiya. SoA-Fog: A Secure Service-Oriented Edge Computing Architecture for Smart Health Big Data Analytics [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2357

Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things

Paper Details

Authors:
Submitted On:
13 November 2017 - 12:54am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Smart Fog_ Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things.pptx

(128 downloads)

Subscribe

[1] , "Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2331. Accessed: Jul. 19, 2018.
@article{2331-17,
url = {http://sigport.org/2331},
author = { },
publisher = {IEEE SigPort},
title = {Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things},
year = {2017} }
TY - EJOUR
T1 - Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2331
ER -
. (2017). Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things. IEEE SigPort. http://sigport.org/2331
, 2017. Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things. Available at: http://sigport.org/2331.
. (2017). "Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things." Web.
1. . Smart Fog: Fog Computing Framework for Telehealth Big Data Analytics in Wearable Internet of Things [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2331

VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY


Large scale images allow pathologists to perform reviews, using
computer workstations instead of microscopes. This trend raises
a wide range of issues related to the management of these massive
datasets. In particular, efficient solutions for data storage and processing
have to be developed in order to deliver increasingly reliable
and faster analyses. In addition, the improvement of workflows also
requires the reinforcement of visualization capabilities. In this paper,
we present a new virtual microscopy (VM) approach for interactivetime

Paper Details

Authors:
Jonathan Sarton, Nicolas Courilleau, Anne-Sophie Hérard, Thierry Delzescaux, Yannick Remion, Laurent Lucas
Submitted On:
16 September 2017 - 1:40am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:

Document Files

Poster_ICIP_2017.pdf

(150 downloads)

Subscribe

[1] Jonathan Sarton, Nicolas Courilleau, Anne-Sophie Hérard, Thierry Delzescaux, Yannick Remion, Laurent Lucas, "VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2177. Accessed: Jul. 19, 2018.
@article{2177-17,
url = {http://sigport.org/2177},
author = {Jonathan Sarton; Nicolas Courilleau; Anne-Sophie Hérard; Thierry Delzescaux; Yannick Remion; Laurent Lucas },
publisher = {IEEE SigPort},
title = {VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY},
year = {2017} }
TY - EJOUR
T1 - VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY
AU - Jonathan Sarton; Nicolas Courilleau; Anne-Sophie Hérard; Thierry Delzescaux; Yannick Remion; Laurent Lucas
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2177
ER -
Jonathan Sarton, Nicolas Courilleau, Anne-Sophie Hérard, Thierry Delzescaux, Yannick Remion, Laurent Lucas. (2017). VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY. IEEE SigPort. http://sigport.org/2177
Jonathan Sarton, Nicolas Courilleau, Anne-Sophie Hérard, Thierry Delzescaux, Yannick Remion, Laurent Lucas, 2017. VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY. Available at: http://sigport.org/2177.
Jonathan Sarton, Nicolas Courilleau, Anne-Sophie Hérard, Thierry Delzescaux, Yannick Remion, Laurent Lucas. (2017). "VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY." Web.
1. Jonathan Sarton, Nicolas Courilleau, Anne-Sophie Hérard, Thierry Delzescaux, Yannick Remion, Laurent Lucas. VIRTUAL REVIEW OF LARGE SCALE IMAGE STACK ON 3D DISPLAY [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2177

Pages