Timezone: »

Picky Learners: Choosing Alternative Ways to Process Data.
Corinna Cortes · Kamalika Chaudhuri · Giulia DeSalvo · Ningshan Zhang · Chicheng Zhang

Thu Aug 10 03:30 PM -- 12:30 AM (PDT) @ C4.6
Event URL: https://sites.google.com/site/rejectionactiveicml/home »

Picky Learners consists of a broad range of learning scenarios where the learner does not simply process every data point blindly, but instead can choose to incorporate them in alternative ways. Despite the growing costs of processing and labelling vast amounts of data, only isolated efforts have tackled this problem primarily in the areas of active learning, learning with rejection and on-line learning with feedback graphs.

In active learning, the learner can choose whether or not to query for a label of each data point, thereby paying different costs for each data point. A key advantage in this setting is that the number of examples queried to learn a concept may be much smaller than the number of examples needed in standard supervised learning. More recently, some have used variations of confidence-based models to determine which labels to query. Confidence-based models lie under the more general framework of learning with rejection, which is a key learning scenario where the algorithm can abstain from making a prediction, at the price of incurring a fixed cost. In this scenario, our picky learners can thus choose to abstain from providing a label. In the on-line setting, one can cast learning with rejection under the more general topic of on-line learning with feedback graphs, a setting that interpolates between bandit and full expert scenario in that the player observes a variety of different expert losses after choosing an action. On-line learning with feedback graphs can then in turn be connected back to active learning where depending on the feedback graph only certain labels are requested.

In short, our picky learners can choose to query for the label (active learning), choose to abstain on the label (learning with rejection) or choose to receive different expert losses (on-line learning with feedback graphs). All of three of these fields attempt in different ways to reduce the cost of processing the data by allowing for picky learners, but the connections between these topics has not been fully explored in terms of both theory and practice. The goal of this workshop is then to bring together researchers and practitioners in these three areas in order to bridge the gap between active learning, learning with rejection, and on-line learning with feedback graphs. We expect that the fruitful collaborations started in this workshop will result in novel research that will help develop each field.

Author Information

Corinna Cortes (Google Research)
Kamalika Chaudhuri (UCSD, Meta AI Research, and FAIR)
Giulia DeSalvo (Google Research)
Ningshan Zhang (Quantitative Research)
Chicheng Zhang (UCSD)

Chicheng Zhang is a PhD candidate in Department of Computer Science and Engineering, UCSD, working with Prof. Kamalika Chaudhuri. Prior to this, he was an undergraduate student in Department of Machine Intelligence, School of EECS, Peking University, China, where he spent a great time studying machine learning theory with Prof. Liwei Wang. In Summer 2015, he was a research intern at Yahoo Labs NYC, mentored by Dr. Alina Beygelzimer. In Summer 2016, he did a second internship at Yahoo Research NYC, working with Dr. Alina Beygelzimer and Dr. Francesco Orabona. His research interest lies in the intersection of theory and applications of machine learning. He is primarily working on active learning and confidence-rated prediction, hoping to give its theoretical guarantees as well as designing practical algorithms.

More from the Same Authors