Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization

1 code implementation • 17 Jun 2024 • Wenkai Yang, Shiqi Shen, Guangyao Shen, Zhi Gong, Yankai Lin

However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models may deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know.

Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision

no code implementations • NeurIPS 2023 • Zeyang Zhang, Xin Wang, Ziwei Zhang, Guangyao Shen, Shiqi Shen, Wenwu Zhu

To address the challenge, we propose a novel Disentangled Self-supervised Graph Neural Architecture Search (DSGAS) model, which is able to discover the optimal architectures capturing various latent graph factors in a self-supervised fashion based on unlabeled graph data.

Disentanglement Neural Architecture Search