Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led interesting advances, it has not been able to tell if models are relying on dataset biases as shortcuts for successful prediction (e.g., using snow cues for recognising snowmobiles). Such biased models fail to generalise when the bias shifts to a different class. The cross-bias generalisation problem has been addressed by de-biasing training data through augmentation or re-sampling, which are often prohibitive due to the data collection cost (e.g., collecting images of a snowmobile on a desert) and the difficulty of quantifying or expressing biases in the first place. In this work, we propose a novel framework to train a de-biased representation by encouraging it to be different from a set of representations that are biased by design. This tactic is feasible in many scenarios where it is much easier to define a set of biased representations than to define and quantify bias. Our experiments and analyses show that our method discourages models from taking bias shortcuts, resulting in improved performances on de-biased test data.
翻译:许多机器学习算法是通过将数据从单一来源分为培训和测试组来进行训练和评价的,虽然这种对分布式学习情景的这种侧重已导致令人感兴趣的进展,但尚不能确定模型是否依赖数据集偏向作为成功预测的捷径(例如,使用雪球标分雪车)。这种偏向模式在偏向转向不同的类别时无法概括。交叉偏向的概括问题通过通过扩大或再抽样来减少偏见的培训数据来解决,由于数据收集成本(例如,收集沙漠上的雪行动图象)以及首先难以量化或表达偏见,这种偏向性往往令人望而望而却步。在这项工作中,我们提出了一个新的框架,通过鼓励它不同于因设计偏向而偏向的一组表达方式来培训一种不偏向的表述方式。在很多情况下,这种策略是可行的,在这种情况下,界定一套偏向的表达方式比界定和量化偏向偏向性要容易得多。我们的实验和分析表明,我们的方法不利于模型采取偏向偏向的捷径,从而改进了对偏向性数据测试的结果。