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 2109.07371cs.LG
收藏

自学习健壮地解释Siamese网络

Self-learn to Explain Siamese Networks Robustly

Lehigh University(里海大学);Laboratory of Trustworthy Distributed Computing and Service (MoE), BUPT(北京邮电大学可信分布式计算与服务教育部重点实验室);University of Illinois at Chicago(伊利诺伊大学芝加哥分校);Worcester Polytechnic Institute(伍斯特理工学院);Department of Chemical and Biomolecular Engineering, Lehigh University(里海大学化学与生物分子工程系)

Chao Chen, Yifan Shen, Guixiang Ma, Xiangnan Kong, Srinivas Rangarajan, Xi Zhang, Sihong Xie

摘要:

学习比较两个对象在数字取证、人脸识别和大脑网络分析等应用中至关重要,特别是在标记数据稀缺且不平衡的情况下。由于这些应用程序会做出高风险的决策,并涉及公平和透明等社会价值观,因此解释学习模型至关重要。我们的目标是研究广泛用于学习比较的连体网络(SN)的事后解释。我们的特点是不稳定的梯度为基础的解释,由于额外的比较对象在SN中,与一个单一的输入实例的架构。我们提出了一个优化框架,从未标记的数据中获得全局不变性,使用自学习来促进针对特定查询参考对的本地解释的稳定性。优化问题可以使用梯度下降-上升(GDA)来解决约束优化,或者SGD来解决KL-发散正则化无约束优化,并具有收敛性证明,特别是当目标函数由于Siamese架构而非凸时。对神经科学和化学工程的表格和图形数据的定量结果和案例研究表明,该框架尊重自学的不变性,同时鲁棒地优化了解释的忠实性和简单性。我们进一步证明了GDA的收敛性实验。

英文摘要:

Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions and involve societal values like fairness and transparency, it is critical to explain the learned models. We aim to study post-hoc explanations of Siamese networks (SN) widely used in learning to compare. We characterize the instability of gradient-based explanations due to the additional compared object in SN, in contrast to architectures with a single input instance. We propose an optimization framework that derives global invariance from unlabeled data using self-learning to promote the stability of local explanations tailored for specific query-reference pairs. The optimization problems can be solved using gradient descent-ascent (GDA) for constrained optimization, or SGD for KL-divergence regularized unconstrained optimization, with convergence proofs, especially when the objective functions are nonconvex due to the Siamese architecture. Quantitative results and case studies on tabular and graph data from neuroscience and chemical engineering show that the framework respects the self-learned invariance while robustly optimizing the faithfulness and simplicity of the explanation. We further demonstrate the convergence of GDA experimentally.

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。

↑