Are We Ready for Semi-Supervised Learning for Big Data? From Theory to Practice
@SIAM-IS20, 8-9JULY 2020 -- VIRTUAL MINI-SYMPOSIUM
@SIAM-IS20, 8-9JULY 2020 -- VIRTUAL MINI-SYMPOSIUM
ORGANISING TEAM
ORGANISING TEAM
OVERVIEW
OVERVIEW
The last years, machine learning has experienced an astonishing development in all domains. It has become the technique to-go for most of existing problems reporting state-of-the-art results in tasks such as classification, segmentation and detection. However, a major drawback of these techniques is the high dependence on a large corpus of labelled data. This might be a strong assumption for a solution, as annotated data contains strong human bias, and for many applications it is expensive and time consuming to obtain labels. Motivated by these drawbacks, different philosophies have experience a fast developments including Semi-Supervised Learning, in which one aims to exploit very small set of label data and a huge amount of unlabelled data. In this session, we aim to discuss the recent developments on semi-supervised learning for real-world problems. In particular, we will highlight the current state-of-the-art techniques, challenges and opportunities. We will address these factors from both theoretical and practical points of view.
The last years, machine learning has experienced an astonishing development in all domains. It has become the technique to-go for most of existing problems reporting state-of-the-art results in tasks such as classification, segmentation and detection. However, a major drawback of these techniques is the high dependence on a large corpus of labelled data. This might be a strong assumption for a solution, as annotated data contains strong human bias, and for many applications it is expensive and time consuming to obtain labels. Motivated by these drawbacks, different philosophies have experience a fast developments including Semi-Supervised Learning, in which one aims to exploit very small set of label data and a huge amount of unlabelled data. In this session, we aim to discuss the recent developments on semi-supervised learning for real-world problems. In particular, we will highlight the current state-of-the-art techniques, challenges and opportunities. We will address these factors from both theoretical and practical points of view.
LINE UP SPEAKERS (CONFIRMED)
LINE UP SPEAKERS (CONFIRMED)
TECHNION
STANFORD UNIVERSITY
UNIVERSITY OF MANCHESTER
MIT
UNIVERSITY OF TEXAS ARLINGTON
UAB and NWPU
SCHEDULE
SCHEDULE
PART 1 (July 8th, 9-11AM EDT): Semi-Supervised Learning: An Applied Perspective
PART 1 (July 8th, 9-11AM EDT): Semi-Supervised Learning: An Applied Perspective
1a. Poisson Learning: Correcting the Bias in Laplacian Learning at Low Label Rates -- Thorpe, Matthew
1a. Poisson Learning: Correcting the Bias in Laplacian Learning at Low Label Rates -- Thorpe, Matthew
1b. Learning Metrics from Teachers: Compact Networks for Image Embedding -- Yu, Lu
1b. Learning Metrics from Teachers: Compact Networks for Image Embedding -- Yu, Lu
1c. Scene Graph Prediction with Limited Labels -- Sunn Chen, Vincent
1c. Scene Graph Prediction with Limited Labels -- Sunn Chen, Vincent
------- BREAK (5 MIN)
------- BREAK (5 MIN)
PART 2 (July 9th, 9-11AM EDT): Semi-Supervised Learning: A Theoretical Perspective
PART 2 (July 9th, 9-11AM EDT): Semi-Supervised Learning: A Theoretical Perspective
2a. False Alarm Prevention by Semi-Supervised Learning on Data Streams -- Wagner, Tal
2a. False Alarm Prevention by Semi-Supervised Learning on Data Streams -- Wagner, Tal
2b. Constructing New Embeddings by Training Spectral Networks -- Gilboa, Guy
2b. Constructing New Embeddings by Training Spectral Networks -- Gilboa, Guy
2C. Probabilistic Semi-supervised Learning via Sparse Graph Structure Learning -- Wang, Li
2C. Probabilistic Semi-supervised Learning via Sparse Graph Structure Learning -- Wang, Li
REGISTRATION FORM: THE EVENT IS FREE BUT REQUIRES REGISTRATION.
REGISTRATION FORM: THE EVENT IS FREE BUT REQUIRES REGISTRATION.
If you want to register to the SIAM-IS20 (FREE REGISTRATION) you can do it in: LINK SIAM-IS20
If you want to register to the SIAM-IS20 (FREE REGISTRATION) you can do it in: LINK SIAM-IS20