Active Learning from Relative Queries
نویسندگان
چکیده
Active learning has been extensively studied and shown to be useful in solving real problems. The typical setting of traditional active learning methods is querying labels from an oracle. This is only possible if an expert exists, which may not be the case in many real world applications. In this paper, we focus on designing easier questions that can be answered by a non-expert. These questions poll relative information as opposed to absolute information and can be even generated from sideinformation. We propose an active learning approach that queries the ordering of the importance of an instance’s neighbors rather than its label. We explore our approach on real datasets and make several interesting discoveries including that querying neighborhood information can be an effective question to ask and sometimes can even yield better performance than querying labels.
منابع مشابه
Active Perceptual Similarity Modeling with Auxiliary Information
Learning a model of perceptual similarity from a collection of objects is a fundamental task in machine learning underlying numerous applications. A common way to learn such a model is from relative comparisons in the form of triplets: responses to queries of the form “Is object a more similar to b than it is to c?”. If no consideration is made in the determination of which queries to ask, exis...
متن کاملEfficient Learning of Trajectory Preferences Using Combined Ratings and Rankings
In this paper we propose an approach for modeling and learning human preferences using a combination of absolute (querying an expert for a numerical value) and relative (asking the expert to select the highest-value option from a set) queries. Our approach uses a Gaussian process regression model with an associated likelihood function that can take into account both pairwise preferences and num...
متن کاملRelational Databases Query Optimization using Hybrid Evolutionary Algorithm
Optimizing the database queries is one of hard research problems. Exhaustive search techniques like dynamic programming is suitable for queries with a few relations, but by increasing the number of relations in query, much use of memory and processing is needed, and the use of these methods is not suitable, so we have to use random and evolutionary methods. The use of evolutionary methods, beca...
متن کاملActive Preference-Based Learning of Reward Functions
Our goal is to efficiently learn reward functions encoding a human’s preferences for how a dynamical system should act. There are two challenges with this. First, in many problems it is difficult for people to provide demonstrations of the desired system trajectory (like a high-DOF robot arm motion or an aggressive driving maneuver), or to even assign how much numerical reward an action or traj...
متن کاملActive Learning of Classes of Recursive Functions by Ultrametric Algorithms
We study active learning of classes of recursive functions by asking value queries about the target function f , where f is from the target class. That is, the query is a natural number x, and the answer to the query is f(x). The complexity measure in this paper is the worst-case number of queries asked. We prove that for some classes of recursive functions ultrametric active learning algorithm...
متن کامل