Search Results for author: Ali Jannesari

Found 39 papers, 6 papers with code

Learn and Search: An Elegant Technique for Object Lookup using Contrastive Learning

no code implementations12 Mar 2024 Chandan Kumar, Jansel Herrera-Gerena, John Just, Matthew Darr, Ali Jannesari

The rapid proliferation of digital content and the ever-growing need for precise object recognition and segmentation have driven the advancement of cutting-edge techniques in the field of object classification and segmentation.

Contrastive Learning Object +4

Unsupervised learning based object detection using Contrastive Learning

no code implementations21 Feb 2024 Chandan Kumar, Jansel Herrera-Gerena, John Just, Matthew Darr, Ali Jannesari

Training image-based object detectors presents formidable challenges, as it entails not only the complexities of object detection but also the added intricacies of precisely localizing objects within potentially diverse and noisy environments.

Contrastive Learning Object +4

OMPGPT: A Generative Pre-trained Transformer Model for OpenMP

no code implementations28 Jan 2024 Le Chen, Arijit Bhattacharjee, Nesreen Ahmed, Niranjan Hasabnis, Gal Oren, Vy Vo, Ali Jannesari

Large language models (LLMs), as epitomized by models like ChatGPT, have revolutionized the field of natural language processing (NLP).

Code Completion Code Generation +3

LEFL: Low Entropy Client Sampling in Federated Learning

1 code implementation29 Dec 2023 Waqwoya Abebe, Pablo Munoz, Ali Jannesari

This enables the server to perform stratified client sampling across clusters in every round.

Federated Learning

CompCodeVet: A Compiler-guided Validation and Enhancement Approach for Code Dataset

no code implementations11 Nov 2023 Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed, Niranjan Hasabnis, Gal Oren, Bin Lei, Ali Jannesari

The evaluation of CompCodeVet on two open-source code datasets shows that CompCodeVet has the ability to improve the training dataset quality for LLMs.

C++ code Code Generation +2

Evaluating and Optimizing the Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on the CAT Benchmark

no code implementations9 Aug 2023 Hung Phan, Ali Jannesari

Our NMT models of learning ASTTrans Representation can boost the Mean Reciprocal Rank of these state-of-the-art code search processes by up to 3. 08% and improve 23. 08% of queries' results over the CAT benchmark.

Code Search Code Translation +4

PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis

1 code implementation NeurIPS 2023 Ali TehraniJamsaz, Quazi Ishtiaque Mahmud, Le Chen, Nesreen K. Ahmed, Ali Jannesari

The remarkable growth and significant success of machine learning have expanded its applications into programming languages and program analysis.

Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models

no code implementations19 May 2023 Sixing Yu, J. Pablo Muñoz, Ali Jannesari

Foundation Models (FMs), such as LLaMA, BERT, GPT, ViT, and CLIP, have demonstrated remarkable success in a wide range of applications, driven by their ability to leverage vast amounts of data for pre-training.

Federated Learning Privacy Preserving +1

Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation

no code implementations9 May 2023 Le Chen, Quazi Ishtiaque Mahmud, Hung Phan, Nesreen K. Ahmed, Ali Jannesari

However, applying machine learning techniques to parallelism detection presents several challenges, such as the lack of an adequate dataset for training, an effective code representation with rich information, and a suitable machine learning model to learn the latent features of code for diverse analyses.

Program Synthesis

Redundancy and Concept Analysis for Code-trained Language Models

no code implementations1 May 2023 Arushi Sharma, Zefu Hu, Christopher Quinn, Ali Jannesari

This approach helps us understand which neurons and layers can be eliminated (redundancy analysis) and where important code properties are located within the network (concept analysis).

Memorization Model Compression +4

Performance Optimization using Multimodal Modeling and Heterogeneous GNN

no code implementations25 Apr 2023 Akash Dutta, Jordi Alcaraz, Ali TehraniJamsaz, Eduardo Cesar, Anna Sikora, Ali Jannesari

There is, thus, a need for a general purpose and efficient tuning approach that can be easily scaled and adapted to various tuning tasks.

Multimodal Deep Learning Scheduling

ParaGraph: Weighted Graph Representation for Performance Optimization of HPC Kernels

no code implementations7 Apr 2023 Ali TehraniJamsaz, Alok Mishra, Akash Dutta, Abid M. Malik, Barbara Chapman, Ali Jannesari

However, even with OpenMP, the developer must choose from among many strategies for exploiting a GPU or a CPU.

Power Constrained Autotuning using Graph Neural Networks

no code implementations22 Feb 2023 Akash Dutta, Jee Choi, Ali Jannesari

Our approach identifies OpenMP configurations at different power constraints that yield a geometric mean performance improvement of more than $25\%$ and $13\%$ over the default OpenMP configuration on a 32-core Skylake and a $16$-core Haswell processor respectively.

Accelerating Domain-aware Deep Learning Models with Distributed Training

no code implementations25 Jan 2023 Aishwarya Sarkar, Chaoqun Lu, Ali Jannesari

We perform extensive experiments on a dataset of 23 watersheds in a northern state of the U. S. and present our findings.

Addressing Data Heterogeneity in Decentralized Learning via Topological Pre-processing

no code implementations16 Dec 2022 Waqwoya Abebe, Ali Jannesari

In this paper, we demonstrate the advantages of constructing a proxy-based locally heterogeneous DL topology to enhance convergence and maintain data privacy.

Resource-Aware Heterogeneous Federated Learning using Neural Architecture Search

no code implementations9 Nov 2022 Sixing Yu, Phuong Nguyen, Waqwoya Abebe, Justin Stanley, Pablo Munoz, Ali Jannesari

RaFL allocates resource-aware models to edge devices using Neural Architecture Search~(NAS) and allows heterogeneous model architecture deployment by knowledge extraction and fusion.

Federated Learning Neural Architecture Search +1

Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusion

no code implementations16 Aug 2022 Duy Phuong Nguyen, Sixing Yu, J. Pablo Muñoz, Ali Jannesari

This method allows efficient multi-model knowledge fusion and the deployment of resource-aware models while preserving model heterogeneity.

Federated Learning Knowledge Distillation

Heterogeneous Graph Neural Networks for Software Effort Estimation

no code implementations22 Jun 2022 Hung Phan, Ali Jannesari

For time performance, we achieve about 570 seconds as the time performance in both three processes: node embedding initialization, model construction, and story point estimation.

Story Point Effort Estimation by Text Level Graph Neural Network

no code implementations6 Mar 2022 Hung Phan, Ali Jannesari

In this paper, we show the potential and possible challenges of Graph Neural Network text classification in story point level estimation.

text-classification Text Classification

Learning Intermediate Representations using Graph Neural Networks for NUMA and Prefetchers Optimization

no code implementations1 Mar 2022 Ali TehraniJamsaz, Mihail Popov, Akash Dutta, Emmanuelle Saillard, Ali Jannesari

This paper demonstrates how the static Intermediate Representation (IR) of the code can guide NUMA/prefetcher optimizations without the prohibitive cost of performance profiling.

Transfer Learning Approaches for Knowledge Discovery in Grid-based Geo-Spatiotemporal Data

no code implementations NeurIPS Workshop AI4Scien 2021 Aishwarya Sarkar, Jien Zhang, Chaoqun Lu, Ali Jannesari

Extracting and meticulously analyzing geo-spatiotemporal features is crucial to recognize intricate underlying causes of natural events, such as floods.

Transfer Learning

Temporal Shift Reinforcement Learning

1 code implementation5 Sep 2021 Deepak George Thomas, Tichakorn Wongpiromsarn, Ali Jannesari

The function approximators employed by traditional image-based Deep Reinforcement Learning (DRL) algorithms usually lack a temporal learning component and instead focus on learning the spatial component.

Decision Making reinforcement-learning +1

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

1 code implementation5 Feb 2021 Sixing Yu, Arya Mazaheri, Ali Jannesari

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources.

Graph Embedding Model Compression +3

Auto Graph Encoder-Decoder for Neural Network Pruning

no code implementations ICCV 2021 Sixing Yu, Arya Mazaheri, Ali Jannesari

We compared our method with rule-based DNN embedding model compression methods to show the effectiveness of our method.

Model Compression Network Pruning +1

HydroDeep -- A Knowledge Guided Deep Neural Network for Geo-Spatiotemporal Data Analysis

no code implementations9 Oct 2020 Aishwarya Sarkar, Jien Zhang, Chaoqun Lu, Ali Jannesari

Due to limited evidence and complex causes of regional climate change, the confidence in predicting fluvial floods remains low.

Time Series Analysis Transfer Learning

Static Neural Compiler Optimization via Deep Reinforcement Learning

no code implementations20 Aug 2020 Rahim Mammadli, Ali Jannesari, Felix Wolf

Provided with sub-sequences constituting LLVM's O3 sequence, our agent learns to outperform the O3 sequence on the set of source codes used for training and achieves competitive performance on the validation set, gaining up to 1. 32x speedup on previously-unseen programs.

Compiler Optimization reinforcement-learning +1

Visual Exploration and Energy-aware Path Planning via Reinforcement Learning

1 code implementation26 Sep 2019 Amir Niaraki, Jeremy Roghair, Ali Jannesari

During an exploration task with sparsely distributed goals and within a UAV's battery life, the proposed architecture could detect more than twice the amount of goal objects compared to the coverage path planning algorithm in moderate wind field.

Autonomous Vehicles object-detection +4

Automatic Repair and Type Binding of Undeclared Variables using Neural Networks

no code implementations14 Jul 2019 Venkatesh Theru Mohan, Ali Jannesari

Deep learning had been used in program analysis for the prediction of hidden software defects using software defect datasets, security vulnerabilities using generative adversarial networks as well as identifying syntax errors by learning a trained neural machine translation on program codes.

Machine Translation Translation +1

Efficient Object Detection Model for Real-Time UAV Applications

no code implementations30 May 2019 Subrahmanyam Vaddi, Chandan Kumar, Ali Jannesari

We propose a deep feature pyramid architecture which makes use of inherent properties of features extracted from Convolutional Networks by capturing more generic features in the images (such as edge, color etc.)

Object object-detection +1

A Metaprogramming and Autotuning Framework for Deploying Deep Learning Applications

no code implementations21 Nov 2016 Matthew W. Moskewicz, Ali Jannesari, Kurt Keutzer

On Qualcomm GPUs, we show that our framework enables productive development of target-specific optimizations, and achieves reasonable absolute performance.

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