Author name cluster

Zongpeng Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

Forgetting Knowledge Localization and Isolation for Continual Forgetting of Pre-trained Vision Models

Zhiwen Yang
Jiehua Zhang
Chenggang Yan
Yuhan Gao
Zongpeng Li
Xichun Sheng
Liang Li

Continual forgetting task aims to continuously remove multiple target knowledge subsets from pre-trained models while maintaining the integrity of remaining knowledge. Existing methods suffer from both incomplete forgetting of target knowledge and unintended forgetting of indistinguishable remaining knowledge. To address these challenges, we propose the forgetting knowledge localization and isolation for continual forgetting in pre-trained vision models which precisely forgets target knowledge while reducing over-forgetting of remaining knowledge. To achieve precise forgetting, we first propose the forgetting knowledge layer localization to explore layers in the model which are more related to forgetting knowledge. Then, we design the forgetting knowledge parameter isolation to isolate the parameters sensitive to forgetting knowledge in these selected layers, mitigating over-forgetting of remaining knowledge. Finally, we fine-tune these isolated parameters and freeze the remaining parameters to achieve efficient forgetting while maintaining high performance on retained datasets. Extensive experimental results demonstrate that our method achieves superior performance over state-of-the-art methods across multiple continual forgetting tasks.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Diffusion Network Inference from Partial Observations

Ting Gan
Keqi Han
Hao Huang
Shi Ying
Yunjun Gao
Zongpeng Li

To infer the structure of a diffusion network from observed diffusion results, existing approaches customarily assume that observed data are complete and contain the final infection status of each node, as well as precise timestamps of node infections. Due to high cost and uncertainties in the monitoring of node infections, exact timestamps are often unavailable in practice, and even the final infection statuses of nodes are sometimes missing. In this work, we study how to carry out diffusion network inference without infection timestamps, using only partial observations of the final infection statuses of nodes. To this end, we iteratively infer the structure of the target diffusion network with observed data and imputed values for missing data, and learn the most likely infection transmission probabilities between nodes w. r. t. current inferred structure, which then help us update the imputation of missing data in turn. Extensive experimental results on both synthetic and real-world networks show that our approach can properly handle missing data and accurately uncover diffusion network structures.

PDF Details

ICML Conference 2020 Conference Paper

Perceptual Generative Autoencoders

Zijun Zhang
Ruixiang Zhang
Zongpeng Li
Yoshua Bengio
Liam Paull

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the difficulties in training generative models. We therefore propose to map both the generated and target distributions to the latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space. Specifically, we enforce the consistency in both the data space and the latent space with theoretically justified data and latent reconstruction losses. The resulting generative model, which we call a perceptual generative autoencoder (PGA), is then trained with a maximum likelihood or variational autoencoder (VAE) objective. With maximum likelihood, PGAs generalize the idea of reversible generative models to unrestricted neural network architectures and arbitrary number of latent dimensions. When combined with VAEs, PGAs substantially improve over the baseline VAEs in terms of sample quality. Compared to other autoencoder-based generative models using simple priors, PGAs achieve state-of-the-art FID scores on CIFAR-10 and CelebA.

Details

NeurIPS Conference 2018 Conference Paper

Removing the Feature Correlation Effect of Multiplicative Noise

Zijun Zhang
Yining Zhang
Zongpeng Li

Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks. From an information perspective, we consider injecting multiplicative noise into a DNN as training the network to solve the task with noisy information pathways, which leads to the observation that multiplicative noise tends to increase the correlation between features, so as to increase the signal-to-noise ratio of information pathways. However, high feature correlation is undesirable, as it increases redundancy in representations. In this work, we propose non-correlating multiplicative noise (NCMN), which exploits batch normalization to remove the correlation effect in a simple yet effective way. We show that NCMN significantly improves the performance of standard multiplicative noise on image classification tasks, providing a better alternative to dropout for batch-normalized networks. Additionally, we present a unified view of NCMN and shake-shake regularization, which explains the performance gain of the latter.

PDF Details

AAAI Conference 2017 Conference Paper

Expectile Matrix Factorization for Skewed Data Analysis

Rui Zhu
Di Niu
Linglong Kong
Zongpeng Li

Matrix factorization is a popular approach to solving matrix estimation problems based on partial observations. Existing matrix factorization is based on least squares and aims to yield a low-rank matrix to interpret the conditional sample means given the observations. However, in many real applications with skewed and extreme data, least squares cannot explain their central tendency or tail distributions, yielding undesired estimates. In this paper, we propose expectile matrix factorization by introducing asymmetric least squares, a key concept in expectile regression analysis, into the matrix factorization framework. We propose an efﬁcient algorithm to solve the new problem based on alternating minimization and quadratic programming. We prove that our algorithm converges to a global optimum and exactly recovers the true underlying low-rank matrices when noise is zero. For synthetic data with skewed noise and a real-world dataset containing web service response times, the proposed scheme achieves lower recovery errors than the existing matrix factorization method based on least squares in a wide range of settings.

PDF Details