Few-Shot Learning with Class Imbalance
This research addresses a critical real-world problem of class imbalance for practitioners deploying FSL models, showing that common assumptions about meta-learning's robustness to imbalance are often incorrect. This is an incremental but important finding for the FSL community.
This paper investigates the impact of class imbalance on Few-Shot Learning (FSL) algorithms, comparing 10 state-of-the-art methods under various imbalance distributions and rebalancing techniques. They found that most FSL methods experience up to a 17% performance drop without mitigation, and classical rebalancing strategies like random oversampling can be highly effective.
Few-Shot Learning (FSL) algorithms are commonly trained through Meta-Learning (ML), which exposes models to batches of tasks sampled from a meta-dataset to mimic tasks seen during evaluation. However, the standard training procedures overlook the real-world dynamics where classes commonly occur at different frequencies. While it is generally understood that class imbalance harms the performance of supervised methods, limited research examines the impact of imbalance on the FSL evaluation task. Our analysis compares 10 state-of-the-art meta-learning and FSL methods on different imbalance distributions and rebalancing techniques. Our results reveal that 1) some FSL methods display a natural disposition against imbalance while most other approaches produce a performance drop by up to 17\% compared to the balanced task without the appropriate mitigation; 2) contrary to popular belief, many meta-learning algorithms will not automatically learn to balance from exposure to imbalanced training tasks; 3) classical rebalancing strategies, such as random oversampling, can still be very effective, leading to state-of-the-art performances and should not be overlooked; 4) FSL methods are more robust against meta-dataset imbalance than imbalance at the task-level with a similar imbalance ratio ($ρ<20$), with the effect holding even in long-tail datasets under a larger imbalance ($ρ=65$).