arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.01798stat.MLcs.AIcs.ITcs.LGmath.IT
收藏

贝叶斯深度学习中近似后验推理在对抗和分布外环境中的分支

Ramifications of Approximate Posterior Inference for Bayesian Deep Learning in Adversarial and Out-of-Distribution Settings

University College Dublin(都柏林大学学院)

John Mitros, Arjun Pakrashi, Brian Mac Namee

摘要:

深度神经网络在不同的判别分类任务中取得了成功,尽管它们的校准很差,通常会将高概率分配给错误分类的预测。潜在的后果可能会导致模型在实际应用中部署时的可信度和问责制,其中预测是根据其置信度评分进行评估的。现有的解决方案表明,通过将深度神经网络和贝叶斯推断相结合来量化模型对模糊数据点预测的不确定性,可以获得好处。在这项工作中,我们提出了验证和测试的有效性,基于似然模型的任务的分布检测(OoD)。在不同的数据集和指标中,我们发现贝叶斯深度学习模型在某些情况下的表现略优于传统的神经网络,并且在输入/输出分布类之间的重叠最小的情况下,即使是最好的模型在检测OoD数据时也会表现出AUC分数的降低。初步调查表明,由于初始化,架构或激活功能的选择偏见的潜在的固有作用。我们假设,神经网络对看不见的输入的敏感性可能是一个多因素的现象,产生于不同的建筑设计选择,往往被维度灾难放大。此外,我们还进行了一项研究,以发现对抗性噪声抵抗方法对分布内和分布外性能的影响,并研究贝叶斯深度学习器的对抗性噪声鲁棒性。

英文摘要:

Deep neural networks have been successful in diverse discriminative classification tasks, although, they are poorly calibrated often assigning high probability to misclassified predictions. Potential consequences could lead to trustworthiness and accountability of the models when deployed in real applications, where predictions are evaluated based on their confidence scores. Existing solutions suggest the benefits attained by combining deep neural networks and Bayesian inference to quantify uncertainty over the models' predictions for ambiguous datapoints. In this work we propose to validate and test the efficacy of likelihood based models in the task of out of distribution detection (OoD). Across different datasets and metrics we show that Bayesian deep learning models on certain occasions marginally outperform conventional neural networks and in the event of minimal overlap between in/out distribution classes, even the best models exhibit a reduction in AUC scores in detecting OoD data. Preliminary investigations indicate the potential inherent role of bias due to choices of initialisation, architecture or activation functions. We hypothesise that the sensitivity of neural networks to unseen inputs could be a multi-factor phenomenon arising from the different architectural design choices often amplified by the curse of dimensionality. Furthermore, we perform a study to find the effect of the adversarial noise resistance methods on in and out-of-distribution performance, as well as, also investigate adversarial noise robustness of Bayesian deep learners.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑