Ahmed M. Abdelmoniem

Karan Gadgil, Sukhpal Singh Gill, Ahmed M. Abdelmoniem

Companies across the globe are keen on targeting potential high-value customers in an attempt to expand revenue and this could be achieved only by understanding the customers more. Customer Lifetime Value (CLV) is the total monetary value of transactions/purchases made by a customer with the business over an intended period of time and is used as means to estimate future customer interactions. CLV finds application in a number of distinct business domains such as Banking, Insurance, Online-entertainment, Gaming, and E-Commerce. The existing distribution-based and basic (recency, frequency & monetary) based models face a limitation in terms of handling a wide variety of input features. Moreover, the more advanced Deep learning approaches could be superfluous and add an undesirable element of complexity in certain application areas. We, therefore, propose a system which is able to qualify both as effective, and comprehensive yet simple and interpretable. With that in mind, we develop a meta-learning-based stacked regression model which combines the predictions from bagging and boosting models that each is found to perform well individually. Empirical tests have been carried out on an openly available Online Retail dataset to evaluate various models and show the efficacy of the proposed approach.

Karan Pardeshi, Sukhpal Singh Gill, Ahmed M. Abdelmoniem

One of the most enticing research areas is the stock market, and projecting stock prices may help investors profit by making the best decisions at the correct time. Deep learning strategies have emerged as a critical technique in the field of the financial market. The stock market is impacted due to two aspects, one is the geo-political, social and global events on the bases of which the price trends could be affected. Meanwhile, the second aspect purely focuses on historical price trends and seasonality, allowing us to forecast stock prices. In this paper, our aim is to focus on the second aspect and build a model that predicts future prices with minimal errors. In order to provide better prediction results of stock price, we propose a new model named Long Short-Term Memory (LSTM) with Sequential Self-Attention Mechanism (LSTM-SSAM). Finally, we conduct extensive experiments on the three stock datasets: SBIN, HDFCBANK, and BANKBARODA. The experimental results prove the effectiveness and feasibility of the proposed model compared to existing models. The experimental findings demonstrate that the root-mean-squared error (RMSE), and R-square (R2) evaluation indicators are giving the best results.

Amna Arouj, Ahmed M. Abdelmoniem

Federated learning (FL) is a newly emerged branch of AI that facilitates edge devices to collaboratively train a global machine learning model without centralizing data and with privacy by default. However, despite the remarkable advancement, this paradigm comes with various challenges. Specifically, in large-scale deployments, client heterogeneity is the norm which impacts training quality such as accuracy, fairness, and time. Moreover, energy consumption across these battery-constrained devices is largely unexplored and a limitation for wide-adoption of FL. To address this issue, we develop EAFL, an energy-aware FL selection method that considers energy consumption to maximize the participation of heterogeneous target devices. EAFL is a power-aware training algorithm that cherry-picks clients with higher battery levels in conjunction with its ability to maximize the system efficiency. Our design jointly minimizes the time-to-accuracy and maximizes the remaining on-device battery levels. EAFLimproves the testing model accuracy by up to 85\% and decreases the drop-out of clients by up to 2.45$\times$.

Shaoyuan Chen, Linlin You, Rui Liu et al.

The training of large models, involving fine-tuning, faces the scarcity of high-quality data. Compared to the solutions based on centralized data centers, updating large models in the Internet of Things (IoT) faces challenges in coordinating knowledge from distributed clients by using their private and heterogeneous data. To tackle such a challenge, we propose KOALA (Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients) to impel the training of large models in IoT. Since the resources obtained by IoT clients are limited and restricted, it is infeasible to locally execute large models and also update them in a privacy-preserving manner. Therefore, we leverage federated learning and knowledge distillation to update large models through collaboration with their small models, which can run locally at IoT clients to process their private data separately and enable large-small model knowledge transfer through iterative learning between the server and clients. Moreover, to support clients with similar or different computing capacities, KOALA is designed with two kinds of large-small model joint learning modes, namely to be homogeneous or heterogeneous. Experimental results demonstrate that compared to the conventional approach, our method can not only achieve similar training performance but also significantly reduce the need for local storage and computing power resources.

Qilei Li, Ahmed M. Abdelmoniem

Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are happening in malicious clients through data poisoning and model poisoning, which can deteriorate the performance of aggregated global model. Existing defense methods typically focus on mitigating specific types of poisoning and are often ineffective against unseen types of attack. These methods also assume an attack happened moderately while is not always holds true in real. Consequently, these methods can significantly fail in terms of accuracy and robustness when detecting and addressing updates from attacked malicious clients. To overcome these challenges, in this work, we propose a simple yet effective framework to detect malicious clients, namely Confidence-Aware Defense (CAD), that utilizes the confidence scores of local models as criteria to evaluate the reliability of local updates. Our key insight is that malicious attacks, regardless of attack type, will cause the model to deviate from its previous state, thus leading to increased uncertainty when making predictions. Therefore, CAD is comprehensively effective for both model poisoning and data poisoning attacks by accurately identifying and mitigating potential malicious updates, even under varying degrees of attacks and data heterogeneity. Experimental results demonstrate that our method significantly enhances the robustness of FL systems against various types of attacks across various scenarios by achieving higher model accuracy and stability.

Ahmed M. Abdelmoniem

With mobile, IoT and sensor devices becoming pervasive in our life and recent advances in Edge Computational Intelligence (e.g., Edge AI/ML), it became evident that the traditional methods for training AI/ML models are becoming obsolete, especially with the growing concerns over privacy and security. This work tries to highlight the key challenges that prohibit Edge AI/ML from seeing wide-range adoption in different sectors, especially for large-scale scenarios. Therefore, we focus on the main challenges acting as adoption barriers for the existing methods and propose a design with a drastic shift from the current ill-suited approaches. The new design is envisioned to be model-centric in which the trained models are treated as a commodity driving the exchange dynamics of collaborative learning in decentralized settings. It is expected that this design will provide a decentralized framework for efficient collaborative learning at scale.

Geofrey Owino, Bernard Shibwabo Kasamani, Ahmed M. Abdelmoniem et al.

Accurate and interpretable classification of infant cry paralinguistics is essential for early detection of neonatal distress and clinical decision support. However, many existing deep learning methods rely on correlation-driven acoustic representations, which makes them vulnerable to noise, spurious cues, and domain shifts across recording environments. We propose DACH-TIC, a Domain-Agnostic Causal-Aware Hierarchical Audio Transformer for robust infant cry classification. The model integrates causal attention, hierarchical representation learning, multi-task supervision, and adversarial domain generalization within a unified framework. DACH-TIC employs a structured transformer backbone with local token-level and global semantic encoders, augmented by causal attention masking and controlled perturbation training to approximate counterfactual acoustic variations. A domain-adversarial objective promotes environment-invariant representations, while multi-task learning jointly optimizes cry type recognition, distress intensity estimation, and causal relevance prediction. The model is evaluated on the Baby Chillanto and Donate-a-Cry datasets, with ESC-50 environmental noise overlays for domain augmentation. Experimental results show that DACH-TIC outperforms state-of-the-art baselines, including HTS-AT and SE-ResNet Transformer, achieving improvements of 2.6 percent in accuracy and 2.2 points in macro-F1 score, alongside enhanced causal fidelity. The model generalizes effectively to unseen acoustic environments, with a domain performance gap of only 2.4 percent, demonstrating its suitability for real-world neonatal acoustic monitoring systems.

Pranav M R, Jayant Chandwani, Ahmed M. Abdelmoniem et al.

Multimodal federated learning (FL) is essential for real-world applications such as autonomous systems and healthcare, where data is distributed across heterogeneous clients with varying and often missing modalities. However, most existing FL approaches assume uniform modality availability, limiting their applicability in practice. We introduce BLOSSOM, a task-agnostic framework for multimodal FL designed to operate under shared and sparsely observed modality conditions. BLOSSOM supports clients with arbitrary modality subsets and enables flexible sharing of model components. To address client and task heterogeneity, we propose a block-wise aggregation strategy that selectively aggregates shared components while keeping task-specific blocks private, enabling partial personalization. We evaluate BLOSSOM on multiple diverse multimodal datasets and analyse the effects of missing modalities and personalization. Our results show that block-wise personalization significantly improves performance, particularly in settings with severe modality sparsity. In modality-incomplete scenarios, BLOSSOM achieves an average performance gain of 18.7% over full-model aggregation, while in modality-exclusive settings the gain increases to 37.7%, highlighting the importance of block-wise learning for practical multimodal FL systems.

Vibhor Agarwal, Aravindh Raman, Nishanth Sastry et al.

The recent development of decentralised and interoperable social networks (such as the "fediverse") creates new challenges for content moderators. This is because millions of posts generated on one server can easily "spread" to another, even if the recipient server has very different moderation policies. An obvious solution would be to leverage moderation tools to automatically tag (and filter) posts that contravene moderation policies, e.g. related to toxic speech. Recent work has exploited the conversational context of a post to improve this automatic tagging, e.g. using the replies to a post to help classify if it contains toxic speech. This has shown particular potential in environments with large training sets that contain complete conversations. This, however, creates challenges in a decentralised context, as a single conversation may be fragmented across multiple servers. Thus, each server only has a partial view of an entire conversation because conversations are often federated across servers in a non-synchronized fashion. To address this, we propose a decentralised conversation-aware content moderation approach suitable for the fediverse. Our approach employs a graph deep learning model (GraphNLI) trained locally on each server. The model exploits local data to train a model that combines post and conversational information captured through random walks to detect toxicity. We evaluate our approach with data from Pleroma, a major decentralised and interoperable micro-blogging network containing 2 million conversations. Our model effectively detects toxicity on larger instances, exclusively trained using their local post information (0.8837 macro-F1). Our approach has considerable scope to improve moderation in decentralised and interoperable social networks such as Pleroma or Mastodon.

Mohammed Aljahdali, Ahmed M. Abdelmoniem, Marco Canini et al.

In Federated Learning (FL), forgetting, or the loss of knowledge across rounds, hampers algorithm convergence, particularly in the presence of severe data heterogeneity among clients. This study explores the nuances of this issue, emphasizing the critical role of forgetting in FL's inefficient learning within heterogeneous data contexts. Knowledge loss occurs in both client-local updates and server-side aggregation steps; addressing one without the other fails to mitigate forgetting. We introduce a metric to measure forgetting granularly, ensuring distinct recognition amid new knowledge acquisition. Leveraging these insights, we propose Flashback, an FL algorithm with a dynamic distillation approach that is used to regularize the local models, and effectively aggregate their knowledge. Across different benchmarks, Flashback outperforms other methods, mitigates forgetting, and achieves faster round-to-target-accuracy, by converging in 6 to 16 rounds.

Sofia Zahri, Hajar Bennouri, Ahmed M. Abdelmoniem

In today's world, the rapid expansion of IoT networks and the proliferation of smart devices in our daily lives, have resulted in the generation of substantial amounts of heterogeneous data. These data forms a stream which requires special handling. To handle this data effectively, advanced data processing technologies are necessary to guarantee the preservation of both privacy and efficiency. Federated learning emerged as a distributed learning method that trains models locally and aggregates them on a server to preserve data privacy. This paper showcases two illustrative scenarios that highlight the potential of federated learning (FL) as a key to delivering efficient and privacy-preserving machine learning within IoT networks. We first give the mathematical foundations for key aggregation algorithms in federated learning, i.e., FedAvg and FedProx. Then, we conduct simulations, using Flower Framework, to show the \textit{efficiency} of these algorithms by training deep neural networks on common datasets and show a comparison between the accuracy and loss metrics of FedAvg and FedProx. Then, we present the results highlighting the trade-off between maintaining privacy versus accuracy via simulations - involving the implementation of the differential privacy (DP) method - in Pytorch and Opacus ML frameworks on common FL datasets and data distributions for both FedAvg and FedProx strategies.

Norah Alballa, Ahmed M. Abdelmoniem, Marco Canini

This research investigates the enhancement of knowledge distillation (KD) processes in pre-trained models, an emerging field in knowledge transfer with significant implications for distributed training and federated learning environments. These environments benefit from reduced communication demands and accommodate various model architectures. Despite the adoption of numerous KD approaches for transferring knowledge among pre-trained models, a comprehensive understanding of KD's application in these scenarios is lacking. Our study conducts an extensive comparison of multiple KD techniques, including standard KD, tuned KD (via optimized temperature and weight parameters), deep mutual learning, and data partitioning KD. We assess these methods across various data distribution strategies to identify the most effective contexts for each. Through detailed examination of hyperparameter tuning, informed by extensive grid search evaluations, we pinpoint when adjustments are crucial to enhance model performance. This paper sheds light on optimal hyperparameter settings for distinct data partitioning scenarios and investigates KD's role in improving federated learning by minimizing communication rounds and expediting the training process. By filling a notable void in current research, our findings serve as a practical framework for leveraging KD in pre-trained models within collaborative and federated learning frameworks.

Sarang S, Harsh D. Chothani, Qilei Li et al.

Federated Learning (FL) has attracted considerable interest due to growing privacy concerns and regulations like the General Data Protection Regulation (GDPR), which stresses the importance of privacy-preserving and fair machine learning approaches. In FL, model training takes place on decentralized data, so as to allow clients to upload a locally trained model and receive a globally aggregated model without exposing sensitive information. However, challenges related to fairness-such as biases, uneven performance among clients, and the "free rider" issue complicates its adoption. In this paper, we examine the use of Mutual Information (MI)-based loss functions to address these concerns. MI has proven to be a powerful method for measuring dependencies between variables and optimizing deep learning models. By leveraging MI to extract essential features and minimize biases, we aim to improve both the fairness and effectiveness of FL systems. Through extensive benchmarking, we assess the impact of MI-based losses in reducing disparities among clients while enhancing the overall performance of FL.

Wentai Wu, Ligang He, Saiqin Long et al.

Data, as an observable form of knowledge, has become one of the most important factors of production for the development of Artificial Intelligence (AI). Meanwhile, increasing legislation and regulations on private and proprietary information results in scattered data sources also known as the "data islands". Although some collaborative learning paradigms such as Federated Learning (FL) can enable privacy-preserving training over decentralized data, they have inherent deficiencies in fairness, costs and reproducibility because of being learning-centric, which greatly limits the way how participants cooperate with each other. In light of this, we present a knowledge-centric paradigm termed Knowledge Augmentation in Federation (KAF), with focus on how to enhance local knowledge through collaborative effort. We provide the suggested system architecture, formulate the prototypical optimization objective, and review emerging studies that employ methodologies suitable for KAF. On our roadmap, with a three-way categorization we describe the methods for knowledge expansion, knowledge filtering, and label and feature space correction in the federation. Further, we highlight several challenges and open questions that deserve more attention from the community. With our investigation, we intend to offer new insights for what collaborative learning can bring back to decentralized data.

Songyuan Li, Jia Hu, Ahmed M. Abdelmoniem et al.

Recent Mixture-of-Experts (MoE)-based large language models (LLMs) such as Qwen-MoE and DeepSeek-MoE are transforming generative AI in natural language processing. However, these models require vast and diverse training data. Federated learning (FL) addresses this challenge by leveraging private data from heterogeneous edge devices for privacy-preserving MoE training. Nonetheless, traditional FL approaches require devices to host local MoE models, which is impractical for resource-constrained devices due to large model sizes. To address this, we propose DeepFusion, the first scalable federated MoE training framework that enables the fusion of heterogeneous on-device LLM knowledge via federated knowledge distillation, yielding a knowledge-abundant global MoE model. Specifically, DeepFusion features each device to independently configure and train an on-device LLM tailored to its own needs and hardware limitations. Furthermore, we propose a novel View-Aligned Attention (VAA) module that integrates multi-stage feature representations from the global MoE model to construct a predictive perspective aligned with on-device LLMs, thereby enabling effective cross-architecture knowledge distillation. By explicitly aligning predictive perspectives, VAA resolves the view-mismatch problem in traditional federated knowledge distillation, which arises from heterogeneity in model architectures and prediction behaviors between on-device LLMs and the global MoE model. Experiments with industry-level MoE models (Qwen-MoE and DeepSeek-MoE) and real-world datasets (medical and finance) demonstrate that DeepFusion achieves performance close to centralized MoE training. Compared with key federated MoE baselines, DeepFusion reduces communication costs by up to 71% and improves token perplexity by up to 5.28%.

Md. Kamrul Hossain, Walid Aljoby, Anis Elgabli et al.

Federated Learning (FL) enables collaborative learning without exposing clients' data. While clients only share model updates with the aggregator, studies reveal that aggregators can infer sensitive information from these updates. Secure Aggregation (SA) protects individual updates during transmission; however, recent work demonstrates a critical vulnerability where adversarial aggregators manipulate client selection to bypass SA protections, constituting a Biased Selection Attack (BSA). Although verifiable random selection prevents BSA, it precludes informed client selection essential for FL performance. We propose Adversarial Robust Federated Learning (AdRo-FL), which simultaneously enables: informed client selection based on client utility, and robust defense against BSA maintaining privacy-preserving aggregation. AdRo-FL implements two client selection frameworks tailored for distinct settings. The first framework assumes clients are grouped into clusters based on mutual trust, such as different branches of an organization. The second framework handles distributed clients where no trust relationships exist between them. For the cluster-oriented setting, we propose a novel defense against BSA by (1) enforcing a minimum client selection quota from each cluster, supervised by a cluster-head in every round, and (2) introducing a client utility function to prioritize efficient clients. For the distributed setting, we design a two-phase selection protocol: first, the aggregator selects the top clients based on our utility-driven ranking; then, a verifiable random function (VRF) ensures a BSA-resistant final selection. AdRo-FL also applies quantization to reduce communication overhead and sets strict transmission deadlines to improve energy efficiency. AdRo-FL achieves up to $1.85\times$ faster time-to-accuracy and up to $1.06\times$ higher final accuracy compared to insecure baselines.

Norah Alballa, Wenxuan Zhang, Ziquan Liu et al.

Decentralized collaborative learning under data heterogeneity and privacy constraints has rapidly advanced. However, existing solutions like federated learning, ensembles, and transfer learning, often fail to adequately serve the unique needs of clients, especially when local data representation is limited. To address this issue, we propose a novel framework called Query-based Knowledge Transfer (QKT) that enables tailored knowledge acquisition to fulfill specific client needs without direct data exchange. QKT employs a data-free masking strategy to facilitate communication-efficient query-focused knowledge transfer while refining task-specific parameters to mitigate knowledge interference and forgetting. Our experiments, conducted on both standard and clinical benchmarks, show that QKT significantly outperforms existing collaborative learning methods by an average of 20.91\% points in single-class query settings and an average of 14.32\% points in multi-class query scenarios. Further analysis and ablation studies reveal that QKT effectively balances the learning of new and existing knowledge, showing strong potential for its application in decentralized learning.

Ahmad Faraz Khan, Samuel Fountain, Ahmed M. Abdelmoniem et al.

Federated Learning (FL) is an approach for privacy-preserving Machine Learning (ML), enabling model training across multiple clients without centralized data collection. With an aggregator server coordinating training, aggregating model updates, and storing metadata across rounds. In addition to training, a substantial part of FL systems are the non-training workloads such as scheduling, personalization, clustering, debugging, and incentivization. Most existing systems rely on the aggregator to handle non-training workloads and use cloud services for data storage. This results in high latency and increased costs as non-training workloads rely on large volumes of metadata, including weight parameters from client updates, hyperparameters, and aggregated updates across rounds, making the situation even worse. We propose FLStore, a serverless framework for efficient FL non-training workloads and storage. FLStore unifies the data and compute planes on a serverless cache, enabling locality-aware execution via tailored caching policies to reduce latency and costs. Per our evaluations, compared to cloud object store based aggregator server FLStore reduces per request average latency by 71% and costs by 92.45%, with peak improvements of 99.7% and 98.8%, respectively. Compared to an in-memory cloud cache based aggregator server, FLStore reduces average latency by 64.6% and costs by 98.83%, with peak improvements of 98.8% and 99.6%, respectively. FLStore integrates seamlessly with existing FL frameworks with minimal modifications, while also being fault-tolerant and highly scalable.

Ahmed M. Abdelmoniem, Atal Narayan Sahu, Marco Canini et al.

Federated Learning (FL) enables distributed training by learners using local data, thereby enhancing privacy and reducing communication. However, it presents numerous challenges relating to the heterogeneity of the data distribution, device capabilities, and participant availability as deployments scale, which can impact both model convergence and bias. Existing FL schemes use random participant selection to improve fairness; however, this can result in inefficient use of resources and lower quality training. In this work, we systematically address the question of resource efficiency in FL, showing the benefits of intelligent participant selection, and incorporation of updates from straggling participants. We demonstrate how these factors enable resource efficiency while also improving trained model quality.

Atal Narayan Sahu, Aritra Dutta, Ahmed M. Abdelmoniem et al.

Gradient compression is a widely-established remedy to tackle the communication bottleneck in distributed training of large deep neural networks (DNNs). Under the error-feedback framework, Top-$k$ sparsification, sometimes with $k$ as little as $0.1\%$ of the gradient size, enables training to the same model quality as the uncompressed case for a similar iteration count. From the optimization perspective, we find that Top-$k$ is the communication-optimal sparsifier given a per-iteration $k$ element budget. We argue that to further the benefits of gradient sparsification, especially for DNNs, a different perspective is necessary -- one that moves from per-iteration optimality to consider optimality for the entire training. We identify that the total error -- the sum of the compression errors for all iterations -- encapsulates sparsification throughout training. Then, we propose a communication complexity model that minimizes the total error under a communication budget for the entire training. We find that the hard-threshold sparsifier, a variant of the Top-$k$ sparsifier with $k$ determined by a constant hard-threshold, is the optimal sparsifier for this model. Motivated by this, we provide convex and non-convex convergence analyses for the hard-threshold sparsifier with error-feedback. Unlike with Top-$k$ sparsifier, we show that hard-threshold has the same asymptotic convergence and linear speedup property as SGD in the convex case and has no impact on the data-heterogeneity in the non-convex case. Our diverse experiments on various DNNs and a logistic regression model demonstrated that the hard-threshold sparsifier is more communication-efficient than Top-$k$.

Ahmed M. Abdelmoniem, Chen-Yu Ho, Pantelis Papageorgiou et al.

Federated learning (FL) is becoming a popular paradigm for collaborative learning over distributed, private datasets owned by non-trusting entities. FL has seen successful deployment in production environments, and it has been adopted in services such as virtual keyboards, auto-completion, item recommendation, and several IoT applications. However, FL comes with the challenge of performing training over largely heterogeneous datasets, devices, and networks that are out of the control of the centralized FL server. Motivated by this inherent setting, we make a first step towards characterizing the impact of device and behavioral heterogeneity on the trained model. We conduct an extensive empirical study spanning close to 1.5K unique configurations on five popular FL benchmarks. Our analysis shows that these sources of heterogeneity have a major impact on both model performance and fairness, thus sheds light on the importance of considering heterogeneity in FL system design.

Ahmed M. Abdelmoniem, Ahmed Elzanaty, Mohamed-Slim Alouini et al.

The recent many-fold increase in the size of deep neural networks makes efficient distributed training challenging. Many proposals exploit the compressibility of the gradients and propose lossy compression techniques to speed up the communication stage of distributed training. Nevertheless, compression comes at the cost of reduced model quality and extra computation overhead. In this work, we design an efficient compressor with minimal overhead. Noting the sparsity of the gradients, we propose to model the gradients as random variables distributed according to some sparsity-inducing distributions (SIDs). We empirically validate our assumption by studying the statistical characteristics of the evolution of gradient vectors over the training process. We then propose Sparsity-Inducing Distribution-based Compression (SIDCo), a threshold-based sparsification scheme that enjoys similar threshold estimation quality to deep gradient compression (DGC) while being faster by imposing lower compression overhead. Our extensive evaluation of popular machine learning benchmarks involving both recurrent neural network (RNN) and convolution neural network (CNN) models shows that SIDCo speeds up training by up to 41:7%, 7:6%, and 1:9% compared to the no-compression baseline, Topk, and DGC compressors, respectively.

Aritra Dutta, El Houcine Bergou, Ahmed M. Abdelmoniem et al.

Compressed communication, in the form of sparsification or quantization of stochastic gradients, is employed to reduce communication costs in distributed data-parallel training of deep neural networks. However, there exists a discrepancy between theory and practice: while theoretical analysis of most existing compression methods assumes compression is applied to the gradients of the entire model, many practical implementations operate individually on the gradients of each layer of the model. In this paper, we prove that layer-wise compression is, in theory, better, because the convergence rate is upper bounded by that of entire-model compression for a wide range of biased and unbiased compression methods. However, despite the theoretical bound, our experimental study of six well-known methods shows that convergence, in practice, may or may not be better, depending on the actual trained model and compression ratio. Our findings suggest that it would be advantageous for deep learning frameworks to include support for both layer-wise and entire-model compression.