Category · 1.2k presentations
Category · 3.8k presentations
Category · 14.8k presentations
Category · 491 presentations
Category · 1.3k presentations
Category · 529 presentations
Category · 3.3k presentations
Category · 599 presentations
Dez 6, 2021
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Sprecher:in · 0 Follower:innen
Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in many domains. However, due to the non-Euclidean nature of data space and the dependencies between samples, designing effective augmentation on graphs is challenging. In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH-Aug) that draws augmented graphs from an explicit target distribution for semi-supervised learning. MH-Aug produces a sequence of augmented graphs from the target distribution enables flexible control of the strength and diversity of augmentation. Since the direct sampling from the complex target distribution is challenging, we adopt the Metropolis-Hastings algorithm to obtain the augmented samples. We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in many domains. However, due to the non-Euclidean nature of data space and the dependencies between samples, designing effective augmentation on graphs is challenging. In this paper, we propose a novel framework Metropolis-Hastings Data Augmentation (MH…
Konto · 128 Follower:innen
Kategorie · 2,4k Präsentationen
Kategorie · 10,8k Präsentationen
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Professionelle Aufzeichnung und Livestreaming – weltweit.
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind