Mingfu Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mingfu Liang has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Boyang Liu
Meta Platforms, Sunnyvale, CA, USA
2 shared publications Haizhao Yang
Purdue University
2 shared publications- Hua Zheng
Meta Platforms, Sunnyvale, CA, USA
2 shared publications - Huayu Li
Meta Platforms, Inc., Menlo Park, CA, USA
2 shared publications - Laming Chen
Meta Platforms, Inc., Menlo Park, CA, USA
2 shared publications - Qinghai Zhou
Meta Platforms, Sunnyvale, CA, USA
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4000-4011
Generalizable Multi-Pass Training of Ads Recommendation Models with Foundation Model Guidance
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4000-4011
Open AccessGeneralizable Multi-Pass Training of Ads Recommendation Models with Foundation Model Guidance
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 344-353
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 344-353
Open AccessExternal Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2549-2561
DVIB: Towards Robust Multimodal Recommender Systems via Variational Information Bottleneck Distillation
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2549-2561
Open AccessDVIB: Towards Robust Multimodal Recommender Systems via Variational Information Bottleneck Distillation
- Open Access
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (04) , 4206-4214
DIANet: Dense-and-Implicit Attention Network
Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple framework that shares an attention module throughout different network layers to encourage the integration of layer-wise information and this parameter-sharing module is referred to as Dense-and-Implicit-Attention (DIA) unit. Many choices of modules can be used in the DIA unit. Since Long Short Term Memory (LSTM) has a capacity of capturing long-distance dependency, we focus on the case when the DIA unit is the modified LSTM (called DIA-LSTM). Experiments on benchmark datasets show that the DIA-LSTM unit is capable of emphasizing layer-wise feature interrelation and leads to significant improvement of image classification accuracy. We further empirically show that the DIA-LSTM has a strong regularization ability on stabilizing the training of deep networks by the experiments with the removal of skip connections (He et al. 2016a) or Batch Normalization (Ioffe and Szegedy 2015) in the whole residual network.
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (04) , 4206-4214
Open AccessDIANet: Dense-and-Implicit Attention Network
Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple framework that shares an attention module throughout different network layers to encourage the integration of layer-wise information and this parameter-sharing module is referred to as Dense-and-Implicit-Attention (DIA) unit. Many choices of modules can be used in the DIA unit. Since Long Short Term Memory (LSTM) has a capacity of capturing long-distance dependency, we focus on the case when the DIA unit is the modified LSTM (called DIA-LSTM). Experiments on benchmark datasets show that the DIA-LSTM unit is capable of emphasizing layer-wise feature interrelation and leads to significant improvement of image classification accuracy. We further empirically show that the DIA-LSTM has a strong regularization ability on stabilizing the training of deep networks by the experiments with the removal of skip connections (He et al. 2016a) or Batch Normalization (Ioffe and Szegedy 2015) in the whole residual network.
- Open Access
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (04) , 4819-4827
Instance Enhancement Batch Normalization: An Adaptive Regulator of Batch Noise
Batch Normalization (BN) (Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but too much noise will harm the performance of networks. In our paper, we offer a new point of view that the self-attention mechanism can help to regulate the noise by enhancing instance-specific information to obtain a better regularization effect. Therefore, we propose an attention-based BN called Instance Enhancement Batch Normalization (IEBN) that recalibrates the information of each channel by a simple linear transformation. IEBN has a good capacity of regulating the batch noise and stabilizing network training to improve generalization even in the presence of two kinds of noise attacks during training. Finally, IEBN outperforms BN with only a light parameter increment in image classification tasks under different network structures and benchmark datasets.
- 3 April 2020
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 34 (04) , 4819-4827
Open AccessInstance Enhancement Batch Normalization: An Adaptive Regulator of Batch Noise
Batch Normalization (BN) (Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but too much noise will harm the performance of networks. In our paper, we offer a new point of view that the self-attention mechanism can help to regulate the noise by enhancing instance-specific information to obtain a better regularization effect. Therefore, we propose an attention-based BN called Instance Enhancement Batch Normalization (IEBN) that recalibrates the information of each channel by a simple linear transformation. IEBN has a good capacity of regulating the batch noise and stabilizing network training to improve generalization even in the presence of two kinds of noise attacks during training. Finally, IEBN outperforms BN with only a light parameter increment in image classification tasks under different network structures and benchmark datasets.