Author name cluster

Minh Pham

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.

7 papers

1 author row

NeurIPS Conference 2025 Conference Paper

When Are Concepts Erased From Diffusion Models?

Kevin Lu
Nicky Kriplani
Rohit Gandikota
Minh Pham
David Bau
Chinmay Hegde
Niv Cohen

In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly these approaches remove the target concept from the model. We begin by proposing two conceptual models for the erasure mechanism in diffusion models: (i) interfering with the model’s internal guidance processes, and (ii) reducing the unconditional likelihood of generating the target concept, potentially removing it entirely. To assess whether a concept has been truly erased from the model, we introduce a comprehensive suite of independent probing techniques: supplying visual context, modifying the diffusion trajectory, applying classifier guidance, and analyzing the model's alternative generations that emerge in place of the erased concept. Our results shed light on the value of exploring concept erasure robustness outside of adversarial text inputs, and emphasize the importance of comprehensive evaluations for erasure in diffusion models.

PDF Details

TMLR Journal 2023 Journal Article

Distributionally Robust Classification on a Data Budget

Benjamin Feuer
Ameya Joshi
Minh Pham
Chinmay Hegde

Real world uses of deep learning require predictable model behavior under distribution shifts. Models such as CLIP show emergent natural distributional robustness comparable to humans, but may require hundreds of millions of training samples. Can we train robust learners in a domain where data is limited? To rigorously address this question, we introduce JANuS (Joint Annotations and Names Set), a collection of four new training datasets with images, labels, and corresponding captions, and perform a series of carefully controlled investigations of factors contributing to robustness in image classification, then compare those results to findings derived from a large-scale meta-analysis. Using this approach, we show that standard ResNet-50 trained with the cross-entropy loss on 2.4 million image samples can attain comparable robustness to a CLIP ResNet-50 trained on 400 million samples. To our knowledge, this is the first result showing (near) state-of-the-art distributional robustness on limited data budgets.

PDF Details

NeurIPS Conference 2022 Conference Paper

FourierFormer: Transformer Meets Generalized Fourier Integral Theorem

Tan Nguyen
Minh Pham
Tam Nguyen
Khai Nguyen
Stanley Osher
Nhat Ho

Multi-head attention empowers the recent success of transformers, the state-of-the-art models that have achieved remarkable success in sequence modeling and beyond. These attention mechanisms compute the pairwise dot products between the queries and keys, which results from the use of unnormalized Gaussian kernels with the assumption that the queries follow a mixture of Gaussian distribution. There is no guarantee that this assumption is valid in practice. In response, we first interpret attention in transformers as a nonparametric kernel regression. We then propose the FourierFormer, a new class of transformers in which the dot-product kernels are replaced by the novel generalized Fourier integral kernels. Different from the dot-product kernels, where we need to choose a good covariance matrix to capture the dependency of the features of data, the generalized Fourier integral kernels can automatically capture such dependency and remove the need to tune the covariance matrix. We theoretically prove that our proposed Fourier integral kernels can efficiently approximate any key and query distributions. Compared to the conventional transformers with dot-product attention, FourierFormers attain better accuracy and reduce the redundancy between attention heads. We empirically corroborate the advantages of FourierFormers over the baseline transformers in a variety of practical applications including language modeling and image classification.

PDF Details

NeurIPS Conference 2022 Conference Paper

Improving Transformer with an Admixture of Attention Heads

Tan Nguyen
Tam Nguyen
Hai Do
Khai Nguyen
Vishwanath Saragadam
Minh Pham
Khuong Duy Nguyen
Nhat Ho

Transformers with multi-head self-attention have achieved remarkable success in sequence modeling and beyond. However, they suffer from high computational and memory complexities for computing the attention matrix at each head. Recently, it has been shown that those attention matrices lie on a low-dimensional manifold and, thus, are redundant. We propose the Transformer with a Finite Admixture of Shared Heads (FiSHformers), a novel class of efficient and flexible transformers that allow the sharing of attention matrices between attention heads. At the core of FiSHformer is a novel finite admixture model of shared heads (FiSH) that samples attention matrices from a set of global attention matrices. The number of global attention matrices is much smaller than the number of local attention matrices generated. FiSHformers directly learn these global attention matrices rather than the local ones as in other transformers, thus significantly improving the computational and memory efficiency of the model. We empirically verify the advantages of the FiSHformer over the baseline transformers in a wide range of practical applications including language modeling, machine translation, and image classification. On the WikiText-103, IWSLT'14 De-En and WMT'14 En-De, FiSHformers use much fewer floating-point operations per second (FLOPs), memory, and parameters compared to the baseline transformers.

PDF Details

IJCAI Conference 2021 Conference Paper

SPADE: A Semi-supervised Probabilistic Approach for Detecting Errors in Tables

Minh Pham
Craig A. Knoblock
Muhao Chen
Binh Vu
Jay Pujara

Error detection is one of the most important steps in data cleaning and usually requires extensive human interaction to ensure quality. Existing supervised methods in error detection require a significant amount of training data while unsupervised methods rely on fixed inductive biases, which are usually hard to generalize, to solve the problem. In this paper, we present SPADE, a novel semi-supervised probabilistic approach for error detection. SPADE introduces a novel probabilistic active learning model, where the system suggests examples to be labeled based on the agreements between user labels and indicative signals, which are designed to capture potential errors. SPADE uses a two-phase data augmentation process to enrich a dataset before training a deep learning classifier to detect unlabeled errors. In our evaluation, SPADE achieves an average F1-score of 0. 91 over five datasets and yields a 10% improvement compared with the state-of-the-art systems.

PDF Details DOI

YNIMG Journal 2018 Journal Article

A low-rank multivariate general linear model for multi-subject fMRI data and a non-convex optimization algorithm for brain response comparison

Tingting Zhang
Minh Pham
Jianhui Sun
Guofen Yan
Huazhang Li
Yinge Sun
Marlen Z. Gonzalez
James A. Coan

The focus of this paper is on evaluating brain responses to different stimuli and identifying brain regions with different responses using multi-subject, stimulus-evoked functional magnetic resonance imaging (fMRI) data. To jointly model many brain voxels’ responses to designed stimuli, we present a new low-rank multivariate general linear model (LRMGLM) for stimulus-evoked fMRI data. The new model not only is flexible to characterize variation in hemodynamic response functions (HRFs) across different regions and stimulus types, but also enables information “borrowing” across voxels and uses much fewer parameters than typical nonparametric models for HRFs. To estimate the proposed LRMGLM, we introduce a new penalized optimization function, which leads to temporally and spatially smooth HRF estimates. We develop an efficient optimization algorithm to minimize the optimization function and identify the voxels with different responses to stimuli. We show that the proposed method can outperform several existing voxel-wise methods by achieving both high sensitivity and specificity. We apply the proposed method to the fMRI data collected in an emotion study, and identify anterior dACC to have different responses to a designed threat and control stimuli.

Details DOI

JMLR Journal 2014 Journal Article

Alternating Linearization for Structured Regularization Problems

Xiaodong Lin
Minh Pham
Andrzej Ruszczyński

We adapt the alternating linearization method for proximal decomposition to structured regularization problems, in particular, to the generalized lasso problems. The method is related to two well-known operator splitting methods, the Douglas--Rachford and the Peaceman--Rachford method, but it has descent properties with respect to the objective function. This is achieved by employing a special update test, which decides whether it is beneficial to make a Peaceman--Rachford step, any of the two possible Douglas--Rachford steps, or none. The convergence mechanism of the method is related to that of bundle methods of nonsmooth optimization. We also discuss implementation for very large problems, with the use of specialized algorithms and sparse data structures. Finally, we present numerical results for several synthetic and real-world examples, including a three-dimensional fused lasso problem, which illustrate the scalability, efficacy, and accuracy of the method. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

PDF Details