Search

In this study, we explore the efficacy of advanced pre-trained architectures, such as Vision Transformers (ViT), ConvNeXt, and Swin Transformers in enhancing Federated Domain Generalization. These architectures capture global contextual features and model long-range dependencies, making them promising candidates for improving cross-domain generalization. We conduct a broad study with in-depth analysis and systematically evaluate different variants of these architectures, using extensive pre-training datasets such as ImageNet-1K, ImageNet-21K, JFT-300M, and ImageNet-22K. Additionally, we compare self-supervised and supervised pre-training strategies to assess their impact on FDG performance. Our findings suggest that self-supervised techniques, which focus on reconstructing masked image patches, can better capture the intrinsic structure of images, thereby outperforming their supervised counterparts. Comprehensive evaluations on the Office-Home and PACS datasets demonstrate that adopting advanced architectures pre-trained on larger datasets establishes new benchmarks, achieving average accuracies of 84.46\% and 92.55\%, respectively. Additionally, we observe that certain variants of these advanced models, despite having fewer parameters, outperform larger ResNet models. This highlights the critical role of utilizing sophisticated architectures and diverse pre-training strategies to enhance FDG performance, especially in scenarios with limited computational resources where model efficiency is crucial. Our results indicate that federated learning systems can become more adaptable and efficient by leveraging these advanced methods, offering valuable insights for future research in FDG.

In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies \cite{li-etal-2020-multi-encoder} have shown that the context encoder generates noise and makes the model robust to the choice of context. This paper further investigates this observation by explicitly modelling context encoding through multi-task learning (MTL) to make the model sensitive to the choice of context. We conduct experiments on cascade MTL architecture, which consists of one encoder and two decoders. Generation of the source from the context is considered an auxiliary task, and generation of the target from the source is the main task. We experimented with German--English language pairs on News, TED, and Europarl corpora. Evaluation results show that the proposed MTL approach performs better than concatenation-based and multi-encoder DocNMT models in low-resource settings and is sensitive to the choice of context. However, we observe that the MTL models are failing to generate the source from the context. These observations align with the previous studies, and this might suggest that the available document-level parallel corpora are not context-aware, and a robust sentence-level model can outperform the context-aware models., Comment: Accepted to EAMT 2024 (poster)

Advancements in 6G wireless technology have elevated the importance of beamforming, especially for attaining ultra-high data rates via millimeter-wave (mmWave) frequency deployment. Although promising, mmWave bands require substantial beam training to achieve precise beamforming. While initial deep learning models that use RGB camera images demonstrated promise in reducing beam training overhead, their performance suffers due to sensitivity to lighting and environmental variations. Due to this sensitivity, Quality of Service (QoS) fluctuates, eventually affecting the stability and dependability of networks in dynamic environments. This emphasizes a critical need for robust solutions. This paper proposes a robust beamforming technique to ensure consistent QoS under varying environmental conditions. An optimization problem has been formulated to maximize users' data rates. To solve the formulated NP-hard optimization problem, we decompose it into two subproblems: the semantic localization problem and the optimal beam selection problem. To solve the semantic localization problem, we propose a novel method that leverages the K-means clustering and YOLOv8 model. To solve the beam selection problem, we propose a novel lightweight hybrid architecture that combines a lightweight transformer with a CNN architecture through a weighted entropy mechanism. This hybrid architecture utilizes multimodal data sources to dynamically predict the optimal beams. A novel metric, Accuracy-Complexity Efficiency (ACE), has been proposed to quantify this. Six testing scenarios have been developed to evaluate the robustness of the proposed model. Finally, the simulation result demonstrates that the proposed model outperforms several state-of-the-art baselines regarding beam prediction accuracy, received power, and ACE in the developed test scenarios.

The last twenty years have seen the development and popularity of network measurement infrastructures. Internet measurement platforms have become common and have demonstrated their relevance in Internet understanding and security observation. However, despite their popularity, those platforms lack of flexibility and reactivity, as they are usually used for longitudinal measurements. As a consequence, they may miss detecting events that are security or Internet-related. During the same period, operating systems have evolved to virtual machines (VMs) as self-contained units for running applications, with the recent rise of unikernels, ultra-lightweight VMs tailored for specific applications, eliminating the need for a host OS. In this paper, we advocate that measurement infrastructures could take advantage of unikernels to become more flexible and efficient. We propose uTNT, a proof-of-concept unikernel-based implementation of TNT, a traceroute extension able to reveal MPLS tunnels. This paper documents the full toolchain for porting TNT into a unikernel and evaluates uTNT performance with respect to more traditional approaches. The paper also discusses a use case in which uTNT could find a suitable usage. uTNT source code is publicly available on Gitlab., Comment: 10 pages, 11 figures, IFIP extended-abstract

Automatic grading and feedback have been long studied using traditional machine learning and deep learning techniques using language models. With the recent accessibility to high performing large language models (LLMs) like LLaMA-2, there is an opportunity to investigate the use of these LLMs for automatic grading and feedback generation. Despite the increase in performance, LLMs require significant computational resources for fine-tuning and additional specific adjustments to enhance their performance for such tasks. To address these issues, Parameter Efficient Fine-tuning (PEFT) methods, such as LoRA and QLoRA, have been adopted to decrease memory and computational requirements in model fine-tuning. This paper explores the efficacy of PEFT-based quantized models, employing classification or regression head, to fine-tune LLMs for automatically assigning continuous numerical grades to short answers and essays, as well as generating corresponding feedback. We conducted experiments on both proprietary and open-source datasets for our tasks. The results show that prediction of grade scores via finetuned LLMs are highly accurate, achieving less than 3% error in grade percentage on average. For providing graded feedback fine-tuned 4-bit quantized LLaMA-2 13B models outperform competitive base models and achieve high similarity with subject matter expert feedback in terms of high BLEU and ROUGE scores and qualitatively in terms of feedback. The findings from this study provide important insights into the impacts of the emerging capabilities of using quantization approaches to fine-tune LLMs for various downstream tasks, such as automatic short answer scoring and feedback generation at comparatively lower costs and latency.

In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transform color values into color classes and vice versa. To optimize the classes, we experiment with different bin sizes for color class transformation. Observing class appearance, standard deviation, and model parameters on various extremely large-scale real-time images in practice we propose 532 color classes for our classification task. During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper saturation of individual objects. We adjust the weights of the major classes, which are more frequently observed, by lowering them, while escalating the weights of the minor classes, which are less commonly observed. In our class re-weight formula, we propose a hyper-parameter for finding the optimal trade-off between the major and minor appeared classes. As we apply regularization to enhance the stability of the minor class, occasional minor noise may appear at the object's edges. We propose a novel object-selective color harmonization method empowered by the Segment Anything Model (SAM) to refine and enhance these edges. We propose two new color image evaluation metrics, the Color Class Activation Ratio (CCAR), and the True Activation Ratio (TAR), to quantify the richness of color components. We compare our proposed model with state-of-the-art models using six different dataset: Place, ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in qualitative and quantitative approaches. The experimental results show that our proposed model outstrips other models in visualization, CNR and in our proposed CCAR and TAR measurement criteria while maintaining satisfactory performance in regression (MSE, PSNR), similarity (SSIM, LPIPS, UIUI), and generative criteria (FID)., Comment: arXiv admin note: text overlap with arXiv:2403.01476

Automatic colorization of gray images with objects of different colors and sizes is challenging due to inter- and intra-object color variation and the small area of the main objects due to extensive backgrounds. The learning process often favors dominant features, resulting in a biased model. In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transform color values into color classes and vice versa. Class optimization and balancing feature distribution are the keys for good performance. Observing class appearance on various extremely large-scale real-time images in practice, we propose 215 color classes for our colorization task. During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper color saturation of individual objects. We establish a trade-off between major and minor classes to provide orthodox class prediction by eliminating major classes' dominance over minor classes. As we apply regularization to enhance the stability of the minor class, occasional minor noise may appear at the object's edges. We propose a novel object-selective color harmonization method empowered by the SAM to refine and enhance these edges. We propose a new color image evaluation metric, the Chromatic Number Ratio (CNR), to quantify the richness of color components. We compare our proposed model with state-of-the-art models using five different datasets: ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in both qualitative and quantitative approaches. The experimental results show that our proposed model outstrips other models in visualization and CNR measurement criteria while maintaining satisfactory performance in regression (MSE, PSNR), similarity (SSIM, LPIPS, UIQI), and generative criteria (FID).

Diabetic Retinopathy (DR) is a prevalent illness associated with Diabetes which, if left untreated, can result in irreversible blindness. Deep Learning based systems are gradually being introduced as automated support for clinical diagnosis. Since healthcare has always been an extremely important domain demanding error-free performance, any adversaries could pose a big threat to the applicability of such systems. In this work, we use Universal Adversarial Perturbations (UAPs) to quantify the vulnerability of Medical Deep Neural Networks (DNNs) for detecting DR. To the best of our knowledge, this is the very first attempt that works on attacking complete fine-grained classification of DR images using various UAPs. Also, as a part of this work, we use UAPs to fine-tune the trained models to defend against adversarial samples. We experiment on several models and observe that the performance of such models towards unseen adversarial attacks gets boosted on average by $3.41$ Cohen-kappa value and maximum by $31.92$ Cohen-kappa value. The performance degradation on normal data upon ensembling the fine-tuned models was found to be statistically insignificant using t-test, highlighting the benefits of UAP-based adversarial fine-tuning.

Community Question-Answering (CQA) portals serve as a valuable tool for helping users within an organization. However, making them accessible to non-English-speaking users continues to be a challenge. Translating questions can broaden the community's reach, benefiting individuals with similar inquiries in various languages. Translating questions using Neural Machine Translation (NMT) poses more challenges, especially in noisy environments, where the grammatical correctness of the questions is not monitored. These questions may be phrased as statements by non-native speakers, with incorrect subject-verb order and sometimes even missing question marks. Creating a synthetic parallel corpus from such data is also difficult due to its noisy nature. To address this issue, we propose a training methodology that fine-tunes the NMT system only using source-side data. Our approach balances adequacy and fluency by utilizing a loss function that combines BERTScore and Masked Language Model (MLM) Score. Our method surpasses the conventional Maximum Likelihood Estimation (MLE) based fine-tuning approach, which relies on synthetic target data, by achieving a 1.9 BLEU score improvement. Our model exhibits robustness while we add noise to our baseline, and still achieve 1.1 BLEU improvement and large improvements on TER and BLEURT metrics. Our proposed methodology is model-agnostic and is only necessary during the training phase. We make the codes and datasets publicly available at \url{https://www.iitp.ac.in/~ai-nlp-ml/resources.html#DomainAdapt} for facilitating further research., Comment: Published at: Findings of EMNLP 2023

Supporting mainstream applications is fundamental for a new OS to have impact. It is generally achieved by developing a layer of compatibility allowing applications developed for a mainstream OS like Linux to run unmodified on the new OS. Building such a layer, as we show, results in large engineering inefficiencies due to the lack of efficient methods to precisely measure the OS features required by a set of applications. We propose Loupe, a novel method based on dynamic analysis that determines the OS features that need to be implemented in a prototype OS to bring support for a target set of applications and workloads. Loupe guides and boosts OS developers as they build compatibility layers, prioritizing which features to implement in order to quickly support many applications as early as possible. We apply our methodology to 100+ applications and several OSes currently under development, demonstrating high engineering effort savings vs. existing approaches: for example, for the 62 applications supported by the OSv kernel, we show that using Loupe, would have required implementing only 37 system calls vs. 92 for the non-systematic process followed by OSv developers. We study our measurements and extract novel key insights. Overall, we show that the burden of building compatibility layers is significantly less than what previous works suggest: in some cases, only as few as 20% of system calls reported by static analysis, and 50% of those reported by naive dynamic analysis need an implementation for an application to successfully run standard benchmarks., Comment: Accepted to appear at ASPLOS'24 (https://www.asplos-conference.org/asplos2024/)

The study investigates the effectiveness of utilizing multimodal information in Neural Machine Translation (NMT). While prior research focused on using multimodal data in low-resource scenarios, this study examines how image features impact translation when added to a large-scale, pre-trained unimodal NMT system. Surprisingly, the study finds that images might be redundant in this context. Additionally, the research introduces synthetic noise to assess whether images help the model deal with textual noise. Multimodal models slightly outperform text-only models in noisy settings, even with random images. The study's experiments translate from English to Hindi, Bengali, and Malayalam, outperforming state-of-the-art benchmarks significantly. Interestingly, the effect of visual context varies with source text noise: no visual context works best for non-noisy translations, cropped image features are optimal for low noise, and full image features work better in high-noise scenarios. This sheds light on the role of visual context, especially in noisy settings, opening up a new research direction for Noisy Neural Machine Translation in multimodal setups. The research emphasizes the importance of combining visual and textual information for improved translation in various environments.

Recent studies have shown that the multi-encoder models are agnostic to the choice of context, and the context encoder generates noise which helps improve the models in terms of BLEU score. In this paper, we further explore this idea by evaluating with context-aware pronoun translation test set by training multi-encoder models trained on three different context settings viz, previous two sentences, random two sentences, and a mix of both as context. Specifically, we evaluate the models on the ContraPro test set to study how different contexts affect pronoun translation accuracy. The results show that the model can perform well on the ContraPro test set even when the context is random. We also analyze the source representations to study whether the context encoder generates noise. Our analysis shows that the context encoder provides sufficient information to learn discourse-level information. Additionally, we observe that mixing the selected context (the previous two sentences in this case) and the random context is generally better than the other settings., Comment: Accepted to MT Summit 2023 (oral)