arXiv subjects

Souvik Kundu

Publications and source records attributed to Souvik Kundu.

At least 91 records · Page 5Linked to original sources

arXiv2023

Federated Learning of Large Models at the Edge via Principal Sub-Model Training

Federated Learning (FL) is emerging as a popular, promising decentralized learning framework that enables collaborative training among clients, with no need to share private data between them or to a centralized server. However, considering many edge clients do not have sufficient computing, memory, or communication capabilities, federated learning of large models still faces significant bottlenecks. To keep such weak but crucial clients in the loop, prior works either consider a heterogeneous-client setting where clients train models with different sizes; or offload training to the server. However, the heterogeneous-client setting requires some clients to train full model, which is not aligned with the resource-constrained setting; while the latter ones break privacy promises in FL when sharing intermediate representations or labels with the server. To overcome these limitations, in this work, we formulate a realistic, but much less explored, cross-device FL setting in which no client can train a full large model nor is willing to share any intermediate information with the remote server. Under such a formulation, we develop a principal sub-model (PriSM) training methodology to collaboratively train a full large model, while assigning each client a small sub-model that is a probabilistic low-rank approximation to the full server model. When creating sub-models, PriSM first performs a principal kernel analysis in the orthogonal kernel space to obtain importance of each kernel. Then, PriSM adopts a novel importance-aware sampling process to select a subset of kernels (i.e., a kernel with high importance is assigned with a higher sampling probability). This sampling process ensures each sub-model is still a low-rank approximation to the full model, while all sub-models together achieve nearly full coverage on the principal kernels.

cs.LG↗

arXiv2023

Competition between Neel, Haldane nematic, plaquette valence bond solid, and $(π,π)$ valence bond solid phases in SU(N) analogs of $S=1$ square-lattice antiferromagnets

We use stochastic series expansion (SSE) quantum Monte Carlo (QMC) methods to study the phases and transitions displayed by a class of sign-free designer Hamiltonians for SU($N$) analogs of spin $S=1$ quantum antiferromagnets on the square lattice. The SU($N$) spins are generators of the single-row two-column representation (complex conjugate of single-row two-column representation) on $A$ ($B$) sublattices of the square lattice, and the Hamiltonian is designed to explore the competition between the nearest neighbour antiferromagnetic exchange couplings $J$ and four-spin interactions $Q$ that favor a plaquette-ordered valence bond solid (p-VBS) ground state. We find that this state is indeed established at large $Q/J$ for all $N > 3$. For $3< N \leq 9$, the ground state exhibits a direct first order quantum phase transition from a small-$Q/J$ Néel ordered antiferromagnetic state to this large-$Q/J$ p-VBS state. The ground state at $Q/J=0$ for $N \geq 10$ has been previously reported to be a valence bond nematic state, dubbed the Haldane nematic in recent literature. For small nonzero $Q/J$ and $N \geq 10$, we additionally find an unusual intermediate state in which the bond energy has a Bragg peak at wavevector $(π,π)$ with no accompanying Bragg peaks at wavevectors $(π,0)$ and $(0, π)$. This $(π, π)$ state also appears to be metastable at $Q/J =0$, as evidenced by low temperature histograms of the Haldane nematic and $(π, π)$ order parameters. Deep in the p-VBS phase of the ground state phase diagram, we find the temperature-driven melting of the p-VBS order is in the Ashkin-Teller universality class. In this regime, we identify an interesting signature of Ashkin-Teller criticality in bond correlations at wavevector $(π, π)$; this is in addition to the expected critical fluctuations of the conventional p-VBS order parameter at wavevectors $(π,0)$ and $(0,π)$.

cond-mat.str-el↗

arXiv2023

Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT

Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fine-tuning. However, their large model sizes often prohibit their applications on resource-constrained edge devices. Existing solutions of yielding parameter-efficient BERT models largely rely on compute-exhaustive training and fine-tuning. Moreover, they often rely on additional compute heavy models to mitigate the performance gap. In this paper, we present Sensi-BERT, a sensitivity driven efficient fine-tuning of BERT models that can take an off-the-shelf pre-trained BERT model and yield highly parameter-efficient models for downstream tasks. In particular, we perform sensitivity analysis to rank each individual parameter tensor, that then is used to trim them accordingly during fine-tuning for a given parameter or FLOPs budget. Our experiments show the efficacy of Sensi-BERT across different downstream tasks including MNLI, QQP, QNLI, SST-2 and SQuAD, showing better performance at similar or smaller parameter budget compared to various alternatives.

cs.CL↗

arXiv2023

InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning

One-Shot Neural Architecture Search (NAS) algorithms often rely on training a hardware agnostic super-network for a domain specific task. Optimal sub-networks are then extracted from the trained super-network for different hardware platforms. However, training super-networks from scratch can be extremely time consuming and compute intensive especially for large models that rely on a two-stage training process of pre-training and fine-tuning. State of the art pre-trained models are available for a wide range of tasks, but their large sizes significantly limits their applicability on various hardware platforms. We propose InstaTune, a method that leverages off-the-shelf pre-trained weights for large models and generates a super-network during the fine-tuning stage. InstaTune has multiple benefits. Firstly, since the process happens during fine-tuning, it minimizes the overall time and compute resources required for NAS. Secondly, the sub-networks extracted are optimized for the target task, unlike prior work that optimizes on the pre-training objective. Finally, InstaTune is easy to "plug and play" in existing frameworks. By using multi-objective evolutionary search algorithms along with lightly trained predictors, we find Pareto-optimal sub-networks that outperform their respective baselines across different performance objectives such as accuracy and MACs. Specifically, we demonstrate that our approach performs well across both unimodal (ViT and BERT) and multi-modal (BEiT-3) transformer based architectures.

cs.LG↗

arXiv2023

FireFly A Synthetic Dataset for Ember Detection in Wildfire

This paper presents "FireFly", a synthetic dataset for ember detection created using Unreal Engine 4 (UE4), designed to overcome the current lack of ember-specific training resources. To create the dataset, we present a tool that allows the automated generation of the synthetic labeled dataset with adjustable parameters, enabling data diversity from various environmental conditions, making the dataset both diverse and customizable based on user requirements. We generated a total of 19,273 frames that have been used to evaluate FireFly on four popular object detection models. Further to minimize human intervention, we leveraged a trained model to create a semi-automatic labeling process for real-life ember frames. Moreover, we demonstrated an up to 8.57% improvement in mean Average Precision (mAP) in real-world wildfire scenarios compared to models trained exclusively on a small real dataset.

cs.CV↗

arXiv2023

C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference

Recently, private inference (PI) has addressed the rising concern over data and model privacy in machine learning inference as a service. However, existing PI frameworks suffer from high computational and communication costs due to the expensive multi-party computation (MPC) protocols. Existing literature has developed lighter MPC protocols to yield more efficient PI schemes. We, in contrast, propose to lighten them by introducing an empirically-defined privacy evaluation. To that end, we reformulate the threat model of PI and use inference data privacy attacks (IDPAs) to evaluate data privacy. We then present an enhanced IDPA, named distillation-based inverse-network attack (DINA), for improved privacy evaluation. Finally, we leverage the findings from DINA and propose C2PI, a two-party PI framework presenting an efficient partitioning of the neural network model and requiring only the initial few layers to be performed with MPC protocols. Based on our experimental evaluations, relaxing the formal data privacy guarantees C2PI can speed up existing PI frameworks, including Delphi [1] and Cheetah [2], up to 2.89x and 3.88x under LAN and WAN settings, respectively, and save up to 2.75x communication costs.

cs.CR↗

arXiv2023

Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference

Large number of ReLU and MAC operations of Deep neural networks make them ill-suited for latency and compute-efficient private inference. In this paper, we present a model optimization method that allows a model to learn to be shallow. In particular, we leverage the ReLU sensitivity of a convolutional block to remove a ReLU layer and merge its succeeding and preceding convolution layers to a shallow block. Unlike existing ReLU reduction methods, our joint reduction method can yield models with improved reduction of both ReLUs and linear operations by up to 1.73x and 1.47x, respectively, evaluated with ResNet18 on CIFAR-100 without any significant accuracy-drop.

cs.LG↗

arXiv2023

Technology-Circuit-Algorithm Tri-Design for Processing-in-Pixel-in-Memory (P2M)

The massive amounts of data generated by camera sensors motivate data processing inside pixel arrays, i.e., at the extreme-edge. Several critical developments have fueled recent interest in the processing-in-pixel-in-memory paradigm for a wide range of visual machine intelligence tasks, including (1) advances in 3D integration technology to enable complex processing inside each pixel in a 3D integrated manner while maintaining pixel density, (2) analog processing circuit techniques for massively parallel low-energy in-pixel computations, and (3) algorithmic techniques to mitigate non-idealities associated with analog processing through hardware-aware training schemes. This article presents a comprehensive technology-circuit-algorithm landscape that connects technology capabilities, circuit design strategies, and algorithmic optimizations to power, performance, area, bandwidth reduction, and application-level accuracy metrics. We present our results using a comprehensive co-design framework incorporating hardware and algorithmic optimizations for various complex real-life visual intelligence tasks mapped onto our P2M paradigm.

eess.IV↗

arXiv2023

ViTA: A Vision Transformer Inference Accelerator for Edge Applications

Vision Transformer models, such as ViT, Swin Transformer, and Transformer-in-Transformer, have recently gained significant traction in computer vision tasks due to their ability to capture the global relation between features which leads to superior performance. However, they are compute-heavy and difficult to deploy in resource-constrained edge devices. Existing hardware accelerators, including those for the closely-related BERT transformer models, do not target highly resource-constrained environments. In this paper, we address this gap and propose ViTA - a configurable hardware accelerator for inference of vision transformer models, targeting resource-constrained edge computing devices and avoiding repeated off-chip memory accesses. We employ a head-level pipeline and inter-layer MLP optimizations, and can support several commonly used vision transformer models with changes solely in our control logic. We achieve nearly 90% hardware utilization efficiency on most vision transformer models, report a power of 0.88W when synthesised with a clock of 150 MHz, and get reasonable frame rates - all of which makes ViTA suitable for edge applications.

cs.AR↗

arXiv2023

Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice significant accuracy. In this paper, we first present a novel measure of non-linearity layers' ReLU sensitivity, enabling mitigation of the time-consuming manual efforts in identifying the same. Based on this sensitivity, we then present SENet, a three-stage training method that for a given ReLU budget, automatically assigns per-layer ReLU counts, decides the ReLU locations for each layer's activation map, and trains a model with significantly fewer ReLUs to potentially yield latency and communication efficient PI. Experimental evaluations with multiple models on various datasets show SENet's superior performance both in terms of reduced ReLUs and improved classification accuracy compared to existing alternatives. In particular, SENet can yield models that require up to ~2x fewer ReLUs while yielding similar accuracy. For a similar ReLU budget SENet can yield models with ~2.32% improved classification accuracy, evaluated on CIFAR-100.

cs.CV↗

arXiv2022

Self-Attentive Pooling for Efficient Deep Learning

Efficient custom pooling techniques that can aggressively trim the dimensions of a feature map and thereby reduce inference compute and memory footprint for resource-constrained computer vision applications have recently gained significant traction. However, prior pooling works extract only the local context of the activation maps, limiting their effectiveness. In contrast, we propose a novel non-local self-attentive pooling method that can be used as a drop-in replacement to the standard pooling layers, such as max/average pooling or strided convolution. The proposed self-attention module uses patch embedding, multi-head self-attention, and spatial-channel restoration, followed by sigmoid activation and exponential soft-max. This self-attention mechanism efficiently aggregates dependencies between non-local activation patches during down-sampling. Extensive experiments on standard object classification and detection tasks with various convolutional neural network (CNN) architectures demonstrate the superiority of our proposed mechanism over the state-of-the-art (SOTA) pooling techniques. In particular, we surpass the test accuracy of existing pooling techniques on different variants of MobileNet-V2 on ImageNet by an average of 1.2%. With the aggressive down-sampling of the activation maps in the initial layers (providing up to 22x reduction in memory consumption), our approach achieves 1.43% higher test accuracy compared to SOTA techniques with iso-memory footprints. This enables the deployment of our models in memory-constrained devices, such as micro-controllers (without losing significant accuracy), because the initial activation maps consume a significant amount of on-chip memory for high-resolution images required for complex vision tasks. Our proposed pooling method also leverages the idea of channel pruning to further reduce memory footprints.

cs.CV↗

arXiv2022

Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs

Existing deep neural networks (DNNs) that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on either activation or weight conditioned convolution operations. However, such conditional learning costs additional multiply-accumulate (MAC) or addition operations, increasing inference memory and compute costs. To that end, we present a sparse mixture once for all adversarial training (SMART), that allows a model to train once and then in-situ trade-off between accuracy and robustness, that too at a reduced compute and parameter overhead. In particular, SMART develops two expert paths, for clean and adversarial images, respectively, that are then conditionally trained via respective dedicated sets of binary sparsity masks. Extensive evaluations on multiple image classification datasets across different models show SMART to have up to 2.72x fewer non-zero parameters costing proportional reduction in compute overhead, while yielding SOTA accuracy-robustness trade-off. Additionally, we present insightful observations in designing sparse masks to successfully condition on both clean and perturbed images.

cs.CV↗

arXiv2022

In-Sensor & Neuromorphic Computing are all you need for Energy Efficient Computer Vision

Due to the high activation sparsity and use of accumulates (AC) instead of expensive multiply-and-accumulates (MAC), neuromorphic spiking neural networks (SNNs) have emerged as a promising low-power alternative to traditional DNNs for several computer vision (CV) applications. However, most existing SNNs require multiple time steps for acceptable inference accuracy, hindering real-time deployment and increasing spiking activity and, consequently, energy consumption. Recent works proposed direct encoding that directly feeds the analog pixel values in the first layer of the SNN in order to significantly reduce the number of time steps. Although the overhead for the first layer MACs with direct encoding is negligible for deep SNNs and the CV processing is efficient using SNNs, the data transfer between the image sensors and the downstream processing costs significant bandwidth and may dominate the total energy. To mitigate this concern, we propose an in-sensor computing hardware-software co-design framework for SNNs targeting image recognition tasks. Our approach reduces the bandwidth between sensing and processing by 12-96x and the resulting total energy by 2.32x compared to traditional CV processing, with a 3.8% reduction in accuracy on ImageNet.

cs.CV↗

arXiv2022

QuantPipe: Applying Adaptive Post-Training Quantization for Distributed Transformer Pipelines in Dynamic Edge Environments

Pipeline parallelism has achieved great success in deploying large-scale transformer models in cloud environments, but has received less attention in edge environments. Unlike in cloud scenarios with high-speed and stable network interconnects, dynamic bandwidth in edge systems can degrade distributed pipeline performance. We address this issue with QuantPipe, a communication-efficient distributed edge system that introduces post-training quantization (PTQ) to compress the communicated tensors. QuantPipe uses adaptive PTQ to change bitwidths in response to bandwidth dynamics, maintaining transformer pipeline performance while incurring limited inference accuracy loss. We further improve the accuracy with a directed-search analytical clipping for integer quantization method (DS-ACIQ), which bridges the gap between estimated and real data distributions. Experimental results show that QuantPipe adapts to dynamic bandwidth to maintain pipeline performance while achieving a practical model accuracy using a wide range of quantization bitwidths, e.g., improving accuracy under 2-bit quantization by 15.85\% on ImageNet compared to naive quantization.

cs.DC↗

arXiv2022

Dynamic Calibration of Nonlinear Sensors with Time-Drifts and Delays by Bayesian Inference

Most sensor calibrations rely on the linearity and steadiness of their response characteristics, but practical sensors are nonlinear, and their response drifts with time, restricting their choices for adoption. To broaden the realm of sensors to allow nonlinearity and time-drift in the underlying dynamics, a Bayesian inference-based nonlinear, non-causal dynamic calibration method is introduced, where the sensed value is estimated as a posterior conditional mean given a finite-length sequence of the sensor measurements and the elapsed time. Additionally, an algorithm is proposed to adjust an already learned calibration map online whenever new data arrives. The effectiveness of the proposed method is validated on continuous-glucose-monitoring (CGM) data from an alive rat equipped with an in-house optical glucose sensor. To allow flexibility in choice, the validation is also performed on a synthetic blood glucose level (BGL) dataset generated using FDA-approved virtual diabetic patient models together with an illustrative CGM sensor model.

eess.SP↗

arXiv2022

Implementation of fast ICA using memristor crossbar arrays for blind image source separations

Independent component analysis is an unsupervised learning approach for computing the independent components (ICs) from the multivariate signals or data matrix. The ICs are evaluated based on the multiplication of the weight matrix with the multivariate data matrix. This study proposes a novel memristor crossbar array for the implementation of both ACY ICA and Fast ICA for blind source separation. The data input was applied in the form of pulse width modulated voltages to the crossbar array and the weight of the implemented neural network is stored in the memristor. The output charges from the memristor columns are used to calculate the weight update, which is executed through the voltages kept higher than the memristor Set/Reset voltages. In order to demonstrate its potential application, the proposed memristor crossbar arrays based fast ICA architecture is employed for image source separation problem. The experimental results demonstrate that the proposed approach is very effective to separate image sources, and also the contrast of the images are improved with an improvement factor in terms of percentage of structural similarity as 67.27% when compared with the software-based implementation of conventional ACY ICA and Fast ICA algorithms.

cs.ET↗

arXiv2022

P2M-DeTrack: Processing-in-Pixel-in-Memory for Energy-efficient and Real-Time Multi-Object Detection and Tracking

Today's high resolution, high frame rate cameras in autonomous vehicles generate a large volume of data that needs to be transferred and processed by a downstream processor or machine learning (ML) accelerator to enable intelligent computing tasks, such as multi-object detection and tracking. The massive amount of data transfer incurs significant energy, latency, and bandwidth bottlenecks, which hinders real-time processing. To mitigate this problem, we propose an algorithm-hardware co-design framework called Processing-in-Pixel-in-Memory-based object Detection and Tracking (P2M-DeTrack). P2M-DeTrack is based on a custom faster R-CNN-based model that is distributed partly inside the pixel array (front-end) and partly in a separate FPGA/ASIC (back-end). The proposed front-end in-pixel processing down-samples the input feature maps significantly with judiciously optimized strided convolution and pooling. Compared to a conventional baseline design that transfers frames of RGB pixels to the back-end, the resulting P2M-DeTrack designs reduce the data bandwidth between sensor and back-end by up to 24x. The designs also reduce the sensor and total energy (obtained from in-house circuit simulations at Globalfoundries 22nm technology node) per frame by 5.7x and 1.14x, respectively. Lastly, they reduce the sensing and total frame latency by an estimated 1.7x and 3x, respectively. We evaluate our approach on the multi-object object detection (tracking) task of the large-scale BDD100K dataset and observe only a 0.5% reduction in the mean average precision (0.8% reduction in the identification F1 score) compared to the state-of-the-art.

eess.IV↗

arXiv2022

Evaluation Benchmarks for Spanish Sentence Representations

Due to the success of pre-trained language models, versions of languages other than English have been released in recent years. This fact implies the need for resources to evaluate these models. In the case of Spanish, there are few ways to systematically assess the models' quality. In this paper, we narrow the gap by building two evaluation benchmarks. Inspired by previous work (Conneau and Kiela, 2018; Chen et al., 2019), we introduce Spanish SentEval and Spanish DiscoEval, aiming to assess the capabilities of stand-alone and discourse-aware sentence representations, respectively. Our benchmarks include considerable pre-existing and newly constructed datasets that address different tasks from various domains. In addition, we evaluate and analyze the most recent pre-trained Spanish language models to exhibit their capabilities and limitations. As an example, we discover that for the case of discourse evaluation tasks, mBERT, a language model trained on multiple languages, usually provides a richer latent representation than models trained only with documents in Spanish. We hope our contribution will motivate a fairer, more comparable, and less cumbersome way to evaluate future Spanish language models.

cs.CL↗