Search Results for author: Maziar Sanjabi

Found 38 papers, 18 papers with code

Modality-specific Distillation

no code implementations NAACL (maiworkshop) 2021 Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, Hamed Firooz

In this paper, we propose modality-specific distillation (MSD) to effectively transfer knowledge from a teacher on multimodal datasets.

Knowledge Distillation Meta-Learning

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning

1 code implementation21 Mar 2024 Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi, Adriana Romero-Soriano, Kamalika Chaudhuri, Mike Rabbat, Chuan Guo

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable.

Memorization Retrieval

Differentially Private Representation Learning via Image Captioning

no code implementations4 Mar 2024 Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo

In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets.

Image Captioning Representation Learning

Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

no code implementations17 Nov 2023 Animesh Sinha, Bo Sun, Anmol Kalia, Arantxa Casanova, Elliot Blanchard, David Yan, Winnie Zhang, Tony Nelli, Jiahui Chen, Hardik Shah, Licheng Yu, Mitesh Kumar Singh, Ankit Ramchandani, Maziar Sanjabi, Sonal Gupta, Amy Bearman, Dhruv Mahajan

Evaluation results show our method improves visual quality by 14%, prompt alignment by 16. 2% and scene diversity by 15. 3%, compared to prompt engineering the base Emu model for stickers generation.

Image Generation Prompt Engineering

Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models

no code implementations7 Oct 2023 Song Jiang, Zahra Shakeri, Aaron Chan, Maziar Sanjabi, Hamed Firooz, Yinglong Xia, Bugra Akyildiz, Yizhou Sun, Jinchao Li, Qifan Wang, Asli Celikyilmaz

Breakdown analysis further highlights RESPROMPT particularly excels in complex multi-step reasoning: for questions demanding at least five reasoning steps, RESPROMPT outperforms the best CoT based benchmarks by a remarkable average improvement of 21. 1% on LLaMA-65B and 14. 3% on LLaMA2-70B.


EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods

no code implementations3 Oct 2023 Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj, Atoosa Malemir Chegini, Daniela Massiceti, Maziar Sanjabi, Shell Xu Hu, Soheil Feizi

From both the human study and automated evaluation, we find that: (i) Instruct-Pix2Pix, Null-Text and SINE are the top-performing methods averaged across different edit types, however {\it only} Instruct-Pix2Pix and Null-Text are able to preserve original image properties; (ii) Most of the editing methods fail at edits involving spatial operations (e. g., changing the position of an object).

Benchmarking text-guided-image-editing

Identifying Interpretable Subspaces in Image Representations

1 code implementation20 Jul 2023 Neha Kalibhat, Shweta Bhardwaj, Bayan Bruss, Hamed Firooz, Maziar Sanjabi, Soheil Feizi

Although many existing approaches interpret features independently, we observe in state-of-the-art self-supervised and supervised models, that less than 20% of the representation space can be explained by individual features.

counterfactual Language Modelling

Augmenting CLIP with Improved Visio-Linguistic Reasoning

no code implementations18 Jul 2023 Samyadeep Basu, Maziar Sanjabi, Daniela Massiceti, Shell Xu Hu, Soheil Feizi

On the challenging Winoground compositional reasoning benchmark, our method improves the absolute visio-linguistic performance of different CLIP models by up to 7%, while on the ARO dataset, our method improves the visio-linguistic performance by upto 3%.

Retrieval Text Retrieval +2

ViP: A Differentially Private Foundation Model for Computer Vision

1 code implementation15 Jun 2023 Yaodong Yu, Maziar Sanjabi, Yi Ma, Kamalika Chaudhuri, Chuan Guo

In this work, we propose as a mitigation measure a recipe to train foundation vision models with differential privacy (DP) guarantee.

Text-To-Concept (and Back) via Cross-Model Alignment

1 code implementation10 May 2023 Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi

We observe that the mapping between an image's representation in one model to its representation in another can be learned surprisingly well with just a linear layer, even across diverse models.

Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

1 code implementation CVPR 2023 Ajinkya Tejankar, Maziar Sanjabi, Qifan Wang, Sinong Wang, Hamed Firooz, Hamed Pirsiavash, Liang Tan

It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on it, the final model will have a backdoor that the adversary can exploit.

Data Poisoning Self-Supervised Learning

Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano

no code implementations24 Oct 2022 Chuan Guo, Alexandre Sablayrolles, Maziar Sanjabi

Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy risks in machine learning.

COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation

no code implementations14 Oct 2022 Nan Wang, Qifan Wang, Yi-Chia Wang, Maziar Sanjabi, Jingzhou Liu, Hamed Firooz, Hongning Wang, Shaoliang Nie

However, the bias inherent in user written text, often used for PTG model training, can inadvertently associate different levels of linguistic quality with users' protected attributes.

counterfactual Counterfactual Inference +4

Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

1 code implementation14 Oct 2022 John Nguyen, Jianyu Wang, Kshitiz Malik, Maziar Sanjabi, Michael Rabbat

Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity.

Federated Learning

FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales

no code implementations2 Jul 2022 Aaron Chan, Shaoliang Nie, Liang Tan, Xiaochang Peng, Hamed Firooz, Maziar Sanjabi, Xiang Ren

Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior.

Hallucination Language Modelling +2

Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

2 code implementations30 Jun 2022 John Nguyen, Jianyu Wang, Kshitiz Malik, Maziar Sanjabi, Michael Rabbat

Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity.

Federated Learning

FedShuffle: Recipes for Better Use of Local Work in Federated Learning

no code implementations27 Apr 2022 Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael Rabbat

The practice of applying several local updates before aggregation across clients has been empirically shown to be a successful approach to overcoming the communication bottleneck in Federated Learning (FL).

Federated Learning

Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

no code implementations Findings (ACL) 2022 Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, Hamed Firooz

Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain.

Decoder Entity Linking +1

Federated Learning with Partial Model Personalization

2 code implementations8 Apr 2022 Krishna Pillutla, Kshitiz Malik, Abdelrahman Mohamed, Michael Rabbat, Maziar Sanjabi, Lin Xiao

We consider two federated learning algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on the devices.

Federated Learning

Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features

no code implementations3 Mar 2022 Neha Kalibhat, Kanika Narang, Hamed Firooz, Maziar Sanjabi, Soheil Feizi

Fine-tuning with Q-Score regularization can boost the linear probing accuracy of SSL models by up to 5. 8% on ImageNet-100 and 3. 7% on ImageNet-1K compared to their baselines.

Linear evaluation Self-Supervised Learning

BARACK: Partially Supervised Group Robustness With Guarantees

no code implementations31 Dec 2021 Nimit S. Sohoni, Maziar Sanjabi, Nicolas Ballas, Aditya Grover, Shaoliang Nie, Hamed Firooz, Christopher Ré

Theoretically, we provide generalization bounds for our approach in terms of the worst-group performance, which scale with respect to both the total number of training points and the number of training points with group labels.

Fairness Generalization Bounds

A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision

no code implementations27 Dec 2021 Ajinkya Tejankar, Maziar Sanjabi, Bichen Wu, Saining Xie, Madian Khabsa, Hamed Pirsiavash, Hamed Firooz

In this paper, we focus on teasing out what parts of the language supervision are essential for training zero-shot image classification models.

Classification Image Captioning +3

UNIREX: A Unified Learning Framework for Language Model Rationale Extraction

1 code implementation BigScience (ACL) 2022 Aaron Chan, Maziar Sanjabi, Lambert Mathias, Liang Tan, Shaoliang Nie, Xiaochang Peng, Xiang Ren, Hamed Firooz

An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction.

Language Modelling text-classification +1

On Tilted Losses in Machine Learning: Theory and Applications

1 code implementation13 Sep 2021 Tian Li, Ahmad Beirami, Maziar Sanjabi, Virginia Smith

Finally, we demonstrate that TERM can be used for a multitude of applications in machine learning, such as enforcing fairness between subgroups, mitigating the effect of outliers, and handling class imbalance.

BIG-bench Machine Learning Fairness +1

Alternating Direction Method of Multipliers for Quantization

no code implementations8 Sep 2020 Tianjian Huang, Prajwal Singhania, Maziar Sanjabi, Pabitra Mitra, Meisam Razaviyayn

For such optimization problems, we study the performance of the Alternating Direction Method of Multipliers for Quantization ($\texttt{ADMM-Q}$) algorithm, which is a variant of the widely-used ADMM method applied to our discrete optimization problem.


Tilted Empirical Risk Minimization

2 code implementations ICLR 2021 Tian Li, Ahmad Beirami, Maziar Sanjabi, Virginia Smith

Empirical risk minimization (ERM) is typically designed to perform well on the average loss, which can result in estimators that are sensitive to outliers, generalize poorly, or treat subgroups unfairly.


Non-convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances

no code implementations15 Jun 2020 Meisam Razaviyayn, Tianjian Huang, Songtao Lu, Maher Nouiehed, Maziar Sanjabi, Mingyi Hong

The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem which is also studied in the context of zero-sum games.

When Does Non-Orthogonal Tensor Decomposition Have No Spurious Local Minima?

no code implementations22 Nov 2019 Maziar Sanjabi, Sina Baharlouei, Meisam Razaviyayn, Jason D. Lee

We study the optimization problem for decomposing $d$ dimensional fourth-order Tensors with $k$ non-orthogonal components.

Tensor Decomposition

Training generative networks using random discriminators

2 code implementations22 Apr 2019 Babak Barazandeh, Meisam Razaviyayn, Maziar Sanjabi

This design helps us to avoid the min-max formulation and leads to an optimization problem that is stable and could be solved efficiently.

Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods

1 code implementation NeurIPS 2019 Maher Nouiehed, Maziar Sanjabi, Tianjian Huang, Jason D. Lee, Meisam Razaviyayn

In this paper, we study the problem in the non-convex regime and show that an \varepsilon--first order stationary point of the game can be computed when one of the player's objective can be optimized to global optimality efficiently.

Federated Optimization in Heterogeneous Networks

19 code implementations14 Dec 2018 Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith

Theoretically, we provide convergence guarantees for our framework when learning over data from non-identical distributions (statistical heterogeneity), and while adhering to device-level systems constraints by allowing each participating device to perform a variable amount of work (systems heterogeneity).

Distributed Optimization Federated Learning

On the Convergence and Robustness of Training GANs with Regularized Optimal Transport

no code implementations NeurIPS 2018 Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee

A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions.

Federated Multi-Task Learning

2 code implementations NeurIPS 2017 Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi, Ameet Talwalkar

Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices.

BIG-bench Machine Learning Federated Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.