paper-with-me

홈 › Papers

Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields

2024-11-08 · Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Fragkiskos D. Malliaros, Michalis Vazirgiannis

Graph Neural Networks (GNNs), which are nowadays the benchmark approach in graph representation learning, have been shown to be vulnerable to adversarial attacks, raising concerns about their real-world applicability. While existing defense techniques primarily concentrate on the training phase of GNNs, involving adjustments to message passing architectures or pre-processing methods, there is a noticeable gap in methods focusing on increasing robustness during inference. In this context, this study introduces RobustCRF, a post-hoc approach aiming to enhance the robustness of GNNs at the inference stage. Our proposed method, founded on statistical relational learning using a Conditional Random Field, is model-agnostic and does not require prior knowledge about the underlying model architecture. We validate the efficacy of this approach across various models, leveraging benchmark node classification datasets.

📄 PDF Abstract BibTeX arXiv:2411.05399

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Representation LearningNode ClassificationRelational ReasoningRepresentation Learning

Similar Papers 제목 키워드 기반

Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement

2025-07-03 · Mostafa Sadeghi, Jean-Eudes Ayilo, Romain Serizel, Xavier Alameda-Pineda arxiv

We explore unsupervised speech enhancement using diffusion models as expressive generative priors for clean speech. Existing approaches guide the reverse diffusion process using noisy speech through an approximate, noise…

Speech Enhancement

AuditVotes: A Framework Towards More Deployable Certified Robustness for Graph Neural Networks

2025-03-29 · Yuni Lai, Yulin Zhu, Yixuan Sun, Yulun Wu 외

Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness. Certified robustness based on randomized smoothing has emerged as a promising solution, offering provable gua…

Computational Efficiency

Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation

2021-08-06 · Ufuk Demir, Atahan Ozer, Yusuf H. Sahin, Gozde Unal

In recent years, deep learning based methods have shown success in essential medical image analysis tasks such as segmentation. Post-processing and refining the results of segmentation is a common practice to decrease th…

Computed Tomography (CT)Medical Image AnalysisPancreas SegmentationSegmentation

Simulation Approaches to General Probabilistic Inference on Belief Networks

2013-03-27 · Ross D. Shachter, Mark Alan Peot

A number of algorithms have been developed to solve probabilistic inference problems on belief networks. These algorithms can be divided into two main groups: exact techniques which exploit the conditional independence r…

Enhancement of Feature Engineering for Conditional Random Field Learning in Chinese Word Segmentation Using Unlabeled Data

2012-09-01 · ROCLINGIJCLCLP 2012 9 · Mike Tian-Jian Jiang, Cheng-Wei Shih, Ting-Hao Yang, Chan-Hung Kuo 외
Chinese Word SegmentationFeature Engineering