Wael AbdAlmageed
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wael AbdAlmageed has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Mohamed E. Hussein.
University of Southern California
7 shared publications - Hanchen Xie
USC Information Sciences Institute
5 shared publications - Premkumar Natarajan
Information Science Institute University of Southern California
4 shared publications - Jiageng Zhu
Department of Electrical and Computer Engineering USC Ming Hsieh
3 shared publications - Jiageng Zhu
USC Information Sciences Institute
3 shared publications - Jiazhi Li
USC Information Sciences Institute
3 shared publications
Latest Publications
- 12 May 2025
- Published by Springer Nature
- p. 170-182
An Investigation on The Position Encoding in Vision-Based Dynamics Prediction
- 12 May 2025
- Published by Springer Nature
- p. 170-182
An Investigation on The Position Encoding in Vision-Based Dynamics Prediction
- Open Access
A Critical Review of Predominant Bias in Neural Networks
Bias issues of neural networks garner significant attention along with its promising advancement. Among various bias issues, mitigating two predominant biases is crucial in advancing fair and trustworthy AI: (1) ensuring neural networks yields even performance across demographic groups, and (2) ensuring algorithmic decision-making does not rely on protected attributes. However, upon the investigation of \pc papers in the relevant literature, we find that there exists a persistent, extensive but under-explored confusion regarding these two types of biases. Furthermore, the confusion has already significantly hampered the clarity of the community and subsequent development of debiasing methodologies. Thus, in this work, we aim to restore clarity by providing two mathematical definitions for these two predominant biases and leveraging these definitions to unify a comprehensive list of papers. Next, we highlight the common phenomena and the possible reasons for the existing confusion. To alleviate the confusion, we provide extensive experiments on synthetic, census, and image datasets, to validate the distinct nature of these biases, distinguish their different real-world manifestations, and evaluate the effectiveness of a comprehensive list of bias assessment metrics in assessing the mitigation of these biases. Further, we compare these two types of biases from multiple dimensions including the underlying causes, debiasing methods, evaluation protocol, prevalent datasets, and future directions. Last, we provide several suggestions aiming to guide researchers engaged in bias-related work to avoid confusion and further enhance clarity in the community.
Open AccessA Critical Review of Predominant Bias in Neural Networks
Bias issues of neural networks garner significant attention along with its promising advancement. Among various bias issues, mitigating two predominant biases is crucial in advancing fair and trustworthy AI: (1) ensuring neural networks yields even performance across demographic groups, and (2) ensuring algorithmic decision-making does not rely on protected attributes. However, upon the investigation of \pc papers in the relevant literature, we find that there exists a persistent, extensive but under-explored confusion regarding these two types of biases. Furthermore, the confusion has already significantly hampered the clarity of the community and subsequent development of debiasing methodologies. Thus, in this work, we aim to restore clarity by providing two mathematical definitions for these two predominant biases and leveraging these definitions to unify a comprehensive list of papers. Next, we highlight the common phenomena and the possible reasons for the existing confusion. To alleviate the confusion, we provide extensive experiments on synthetic, census, and image datasets, to validate the distinct nature of these biases, distinguish their different real-world manifestations, and evaluate the effectiveness of a comprehensive list of bias assessment metrics in assessing the mitigation of these biases. Further, we compare these two types of biases from multiple dimensions including the underlying causes, debiasing methods, evaluation protocol, prevalent datasets, and future directions. Last, we provide several suggestions aiming to guide researchers engaged in bias-related work to avoid confusion and further enhance clarity in the community.
- 5 December 2024
- Published by Springer Nature
- p. 356-371
TRIGS: Trojan Identification from Gradient-Based Signatures
- 5 December 2024
- Published by Springer Nature
- p. 356-371
TRIGS: Trojan Identification from Gradient-Based Signatures
- 2 December 2024
- Published by Springer Nature
- p. 298-313
Large Multimodal Models Thrive with Little Data for Image Emotion Prediction
- 2 December 2024
- Published by Springer Nature
- p. 298-313
Large Multimodal Models Thrive with Little Data for Image Emotion Prediction
- Open Access
DiffusionCounterfactuals: Inferring High-dimensional Counterfactuals with Guidance of Causal Representations
Accurate estimation of counterfactual outcomes in high-dimensional data is crucial for decision-making and understanding causal relationships and intervention outcomes in various domains, including healthcare, economics, and social sciences. However, existing methods often struggle to generate accurate and consistent counterfactuals, particularly when the causal relationships are complex. We propose a novel framework that incorporates causal mechanisms and diffusion models to generate high-quality counterfactual samples guided by causal representation. Our approach introduces a novel, theoretically grounded training and sampling process that enables the model to consistently generate accurate counterfactual high-dimensional data under multiple intervention steps. Experimental results on various synthetic and real benchmarks demonstrate the proposed approach outperforms state-of-the-art methods in generating accurate and high-quality counterfactuals, using different evaluation metrics.
Open AccessDiffusionCounterfactuals: Inferring High-dimensional Counterfactuals with Guidance of Causal Representations
Accurate estimation of counterfactual outcomes in high-dimensional data is crucial for decision-making and understanding causal relationships and intervention outcomes in various domains, including healthcare, economics, and social sciences. However, existing methods often struggle to generate accurate and consistent counterfactuals, particularly when the causal relationships are complex. We propose a novel framework that incorporates causal mechanisms and diffusion models to generate high-quality counterfactual samples guided by causal representation. Our approach introduces a novel, theoretically grounded training and sampling process that enables the model to consistently generate accurate counterfactual high-dimensional data under multiple intervention steps. Experimental results on various synthetic and real benchmarks demonstrate the proposed approach outperforms state-of-the-art methods in generating accurate and high-quality counterfactuals, using different evaluation metrics.
- Open Access
SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed, their limitations remain under-explored. To that end, in this work, we mathematically and empirically reveal the limitation of existing attribute bias removal methods in presence of strong bias and propose a new method that can mitigate this limitation. Specifically, we first derive a general non-vacuous information-theoretical upper bound on the performance of any attribute bias removal method in terms of the bias strength, revealing that they are effective only when the inherent bias in the dataset is relatively weak. Next, we derive a necessary condition for the existence of any method that can remove attribute bias regardless of the bias strength. Inspired by this condition, we then propose a new method using an adversarial objective that directly filters out protected attributes in the input space while maximally preserving all other attributes, without requiring any specific target label. The proposed method achieves state-of-the-art performance in both strong and moderate bias settings. We provide extensive experiments on synthetic, image, and census datasets, to verify the derived theoretical bound and its consequences in practice, and evaluate the effectiveness of the proposed method in removing strong attribute bias.
Open AccessSABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering
Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed, their limitations remain under-explored. To that end, in this work, we mathematically and empirically reveal the limitation of existing attribute bias removal methods in presence of strong bias and propose a new method that can mitigate this limitation. Specifically, we first derive a general non-vacuous information-theoretical upper bound on the performance of any attribute bias removal method in terms of the bias strength, revealing that they are effective only when the inherent bias in the dataset is relatively weak. Next, we derive a necessary condition for the existence of any method that can remove attribute bias regardless of the bias strength. Inspired by this condition, we then propose a new method using an adversarial objective that directly filters out protected attributes in the input space while maximally preserving all other attributes, without requiring any specific target label. The proposed method achieves state-of-the-art performance in both strong and moderate bias settings. We provide extensive experiments on synthetic, image, and census datasets, to verify the derived theoretical bound and its consequences in practice, and evaluate the effectiveness of the proposed method in removing strong attribute bias.
- Open Access
- 2 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 403-414
TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization
The evaluation datasets and metrics for image manipulation detection and localization (IMDL) research have been standardized. But the training dataset for such a task is still nonstandard. Previous researchers have used unconventional and deviating datasets to train neural networks for detecting image forgeries and localizing pixel maps of manipulated regions. For a fair comparison, the training set, test set, and evaluation metrics should be persistent. Hence, comparing the existing methods may not seem fair as the results depend heavily on the training datasets as well as the model architecture. Moreover, none of the previous works release the synthetic training dataset used for the IMDL task. We propose a standardized benchmark training dataset for image splicing, copy-move forgery, removal forgery, and image enhancement forgery. Furthermore, we identify the problems with the existing IMDL datasets and propose the required modifications. We also train the state-of-the-art IMDL methods on our proposed TrainFors 1 dataset for a fair evaluation and report the actual performance of these methods under similar conditions.
- 2 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 403-414
Open AccessTrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization
The evaluation datasets and metrics for image manipulation detection and localization (IMDL) research have been standardized. But the training dataset for such a task is still nonstandard. Previous researchers have used unconventional and deviating datasets to train neural networks for detecting image forgeries and localizing pixel maps of manipulated regions. For a fair comparison, the training set, test set, and evaluation metrics should be persistent. Hence, comparing the existing methods may not seem fair as the results depend heavily on the training datasets as well as the model architecture. Moreover, none of the previous works release the synthetic training dataset used for the IMDL task. We propose a standardized benchmark training dataset for image splicing, copy-move forgery, removal forgery, and image enhancement forgery. Furthermore, we identify the problems with the existing IMDL datasets and propose the required modifications. We also train the state-of-the-art IMDL methods on our proposed TrainFors 1 dataset for a fair evaluation and report the actual performance of these methods under similar conditions.
- 16 February 2023
- Published by Springer Nature
- p. 73-87
SW-VAE: Weakly Supervised Learn Disentangled Representation via Latent Factor Swapping
- 16 February 2023
- Published by Springer Nature
- p. 73-87
SW-VAE: Weakly Supervised Learn Disentangled Representation via Latent Factor Swapping
- 12 February 2023
- Published by Springer Nature
- p. 382-395
Weakly Supervised Invariant Representation Learning via Disentangling Known and Unknown Nuisance Factors
- 12 February 2023
- Published by Springer Nature
- p. 382-395
Weakly Supervised Invariant Representation Learning via Disentangling Known and Unknown Nuisance Factors
- 12 February 2023
- Published by Springer Nature
- p. 363-381
CAT: Controllable Attribute Translation for Fair Facial Attribute Classification
- 12 February 2023
- Published by Springer Nature
- p. 363-381
CAT: Controllable Attribute Translation for Fair Facial Attribute Classification