Zhiyuan Wu

• Wu, Zhiyuan; Choi, Changkyu; Yu, Shujian; Jenssen, Robert & Ramezani-Kebrya, Ali (2026). Mitigating Embedding Leakage via Latent Disruption with Controlled Reconstruction. Transactions on Machine Learning Research (TMLR). doi: https:/openreview.net/forum?id=nZWBrxJyrS. Fulltekst i vitenarkiv Vis sammendrag

  Pre-trained encoders produce semantically rich latent embeddings, which, however, may expose unintended information through malicious inference or exploitation. We propose SEAL, a framework that mitigates embedding leakage by disrupting latent representations based on information-theoretic principles. It reduces the risk of potential misuse while enabling controlled reconstruction for trusted users. SEAL learns to encode controlled perturbations by minimizing the Matrix Norm-based Quadratic Mutual Information (MQMI) functional between original and perturbed embeddings within a hyperspherical latent space. Meanwhile, a private decoder, jointly trained with the SEAL encoder, is trained to reconstruct the original data that is accessible only to authorized users under an access-controlled setting. Extensive experiments on vision and text datasets demonstrate that SEAL reduces latent leakage, weakens the effectiveness of evaluated inference attacks, and preserves reconstruction under the considered setting.

• Wu, Zhiyuan; Choi, Changkyu; Cao, Xiangcheng; Cevher, Volkan & Ramezani-Kebrya, Ali (2025). Addressing Label Shift in Distributed Learning via Entropy Regularization​. International Conference on Learning Representations. Fulltekst i vitenarkiv Vis sammendrag

  We address the challenge of minimizing "true risk" in multi-node distributed learning.\footnote{We use the term node to refer to a client, FPGA, APU, CPU, GPU, or worker.} These systems are frequently exposed to both inter-node and intra-node "label shifts", which present a critical obstacle to effectively optimizing model performance while ensuring that data remains confined to each node. To tackle this, we propose the Versatile Robust Label Shift (VRLS) method, which enhances the maximum likelihood estimation of the test-to-train label importance ratio. VRLS incorporates Shannon entropy-based regularization and adjusts the importance ratio during training to better handle label shifts at the test time. In multi-node learning environments, VRLS further extends its capabilities by learning and adapting importance ratios across nodes, effectively mitigating label shifts and improving overall model performance. Experiments conducted on MNIST, Fashion MNIST, and CIFAR-10 demonstrate the effectiveness of VRLS, outperforming baselines by up to 20% in imbalanced settings. These results highlight the significant improvements VRLS offers in addressing label shifts. Our theoretical analysis further supports this by establishing high-probability bounds on estimation errors.

Se alle arbeider i NVA

• Wu, Zhiyuan (2025). Addressing Label Shift in Distributed Learning via Entropy Regularization. doi: https:/www.youtube.com/watch?v=FRFAxS94Kow. Fulltekst i vitenarkiv

Se alle arbeider i NVA