On Class Orderings for Incremental Learning
The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can have a significant impact on performance and the ranking of the methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Incremental LearningSimilar Papers 제목 키워드 기반
Efficiently Exploring Ordering Problems through Conflict-directed Search
In planning and scheduling, solving problems with both state and temporal constraints is hard since these constraints may be highly coupled. Judicious orderings of events enable solvers to efficiently make decisions over…
BenchmarkingSchedulingAre Greedy Task Orderings Better Than Random in Continual Linear Regression?
We analyze task orderings in continual learning for linear regression, assuming joint realizability of training data. We focus on orderings that greedily maximize dissimilarity between consecutive tasks, a concept briefl…
Continual LearningImproving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models. However, there is little attempt to combine these two types of models, which inituitively possess complementar…
SentenceSentence OrderingConcordance and the Smallest Covering Set of Preference Orderings
Preference orderings are orderings of a set of items according to the preferences (of judges). Such orderings arise in a variety of domains, including group decision making, consumer marketing, voting and machine learnin…
Decision MakingMarketingAsynchronous Federated Continual Learning
The standard class-incremental continual learning setting assumes a set of tasks seen one after the other in a fixed and predefined order. This is not very realistic in federated learning environments where each client w…
Continual LearningFederated Learning