Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision
One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be addressed by simply using more data from the same distribution. We propose an auxiliary training objective that improves the generalization capabilities of neural networks by leveraging an overlooked supervisory signal found in existing datasets. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. We show that such pairs can be identified in a number of existing datasets in computer vision (visual question answering, multi-label image classification) and natural language processing (sentiment analysis, natural language inference). The new training objective orients the gradient of a model's decision function with pairs of counterfactual examples. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualimage-classificationImage ClassificationMulti-Label Image ClassificationNatural Language InferenceQuestion AnsweringSentiment AnalysisVisual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
On Quantitative Evaluations of Counterfactuals
As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metrics do capture and equally important what…
counterfactualHyConEx: Hypernetwork classifier with counterfactual explanations
In recent years, there has been a growing interest in explainable AI methods. We want not only to make accurate predictions using sophisticated neural networks but also to understand what the model's decision is based on…
counterfactualFrom What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI
Counterfactuals play a pivotal role in the two distinct data science fields of causal inference (CI) and explainable artificial intelligence (XAI). While the core idea behind counterfactuals remains the same in both fiel…
Causal InferencecounterfactualExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Semantics and explanation: why counterfactual explanations produce adversarial examples in deep neural networks
Recent papers in explainable AI have made a compelling case for counterfactual modes of explanation. While counterfactual explanations appear to be extremely effective in some instances, they are formally equivalent to a…
counterfactualIfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions
Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this a…
counterfactualCounterfactual ReasoningOpen-Domain Question AnsweringQuestion Answering+1