paper-with-me

홈 › Papers

A Causal View on Robustness of Neural Networks

2020-05-03 · Cheng Zhang, Kun Zhang, Yingzhen Li

We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal manipulation augmented model (deep CAMA) which explicitly models possible manipulations on certain causes leading to changes in the observed effect. We further develop data augmentation and test-time fine-tuning methods to improve deep CAMA's robustness. When compared with discriminative deep neural networks, our proposed model shows superior robustness against unseen manipulations. As a by-product, our model achieves disentangled representation which separates the representation of manipulations from those of other latent causes.

📄 PDF Abstract BibTeX arXiv:2005.01095

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Causality in cognitive neuroscience: concepts, challenges, and distributional robustness

2020-02-14 · Sebastian Weichwald, Jonas Peters

While probabilistic models describe the dependence structure between observed variables, causal models go one step further: they predict, for example, how cognitive functions are affected by external interventions that p…

Causal Inference

Provable Guarantees on the Robustness of Decision Rules to Causal Interventions

2021-05-19 · Benjie Wang, Clare Lyle, Marta Kwiatkowska

Robustness of decision rules to shifts in the data-generating process is crucial to the successful deployment of decision-making systems. Such shifts can be viewed as interventions on a causal graph, which capture (possi…

Decision Making

Causal Representation Learning with Observational Grouping for CXR Classification

2025-06-25 · Rajat Rasal, Avinash Kori, Ben Glocker

Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustn…

Representation Learning

Deconfounding and Causal Regularization for Stability and External Validity

2020-08-14 · Peter Bühlmann, Domagoj Ćevid

We review some recent work on removing hidden confounding and causal regularization from a unified viewpoint. We describe how simple and user-friendly techniques improve stability, replicability and distributional robust…

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference

2024-03-02 · Jialong Wu, Linhai Zhang, Deyu Zhou, Guoqiang Xu

Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transfor…

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Causal Inferencecounterfactual+2