Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models
We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each expert explains a subset of data using First Order Logic (FOL). While explaining a sample, the FOL from biased BB-derived MoIE detects the shortcut effectively. Finetuning the BB with Metadata Normalization (MDN) eliminates the shortcut. The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut. Our experiments show that MoIE does not hurt the accuracy of the original BB and eliminates shortcuts effectively.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities
An important pillar for safe machine learning (ML) is the systematic mitigation of weaknesses in neural networks to afford their deployment in critical applications. An ubiquitous class of safety risks are learned shortc…
Autonomous DrivingDividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models are inherently explainable. Yet, interpr…
ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset
Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets i…
Natural Language UnderstandingGenerative Poisoning Using Random Discriminators
We introduce ShortcutGen, a new data poisoning attack that generates sample-dependent, error-minimizing perturbations by learning a generator. The key novelty of ShortcutGen is the use of a randomly-initialized discrimin…
Data PoisoningThe Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
Multimodal Reward Models (MM-RMs) are crucial for aligning Large Language Models (LLMs) with human preferences, particularly as LLMs increasingly interact with multimodal data. However, we find that MM-RMs trained on exi…