Distributed time series data presents a challenge for federated learning, as clients often possess different feature sets and have misaligned time steps. Existing federated time series models are limited by the assumption of perfect temporal or feature alignment across clients. In this paper, we propose FedTDD, a novel federated time series diffusion model that jointly learns a synthesizer across clients. At the core of FedTDD is a novel data distillation and aggregation framework that reconciles the differences between clients by imputing the misaligned timesteps and features. In contrast to traditional federated learning, FedTDD learns the correlation across clients’ time series through the exchange of local synthetic outputs instead of model parameters. A coordinator iteratively improves a global distiller network by leveraging shared knowledge from clients through the exchange of synthetic data. As the distiller becomes more refined over time, it subsequently enhances the quality of the clients’ local feature estimates, allowing each client to then improve its local imputations for missing data using the latest, more accurate distiller. Experimental results on five datasets demonstrate FedTDD ’s effectiveness compared to centralized training, and the effectiveness of sharing synthetic outputs to transfer knowledge of local time series. Notably, FedTDD achieves 79.4% and 62.8% improvement over local training in Context-FID and Correlational scores. Our code is available at: https://github.com/soizhiwen/FedTDD.

Vehicles are transforming from transportation means to mobile intelligent terminals, powered by artificial intelligence (AI) technologies such as large language (LLM) and vision large models (VLM). To maintain high learning accuracy in all situations, in-vehicle AI models encounter the acute need to continuously learn and dynamically retrain AI models on the fly. The volatile resource demands of such stochastic retraining jobs and inference jobs of higher priority however can not be accommodated simultaneously by existing training systems, which rely on pre-generated compressed models of fixed architecture. In this paper, we propose ConvertNet, a novel continuous learning system that effectively scales up/down a compressed model through training-time neuron memorizer (TNM) - a max heap of neurons in tree structure. Based on TNM, ConvertNet estimates the model's resource-accuracy trade-off per neuron, thus efficiently utilizing the limited available resources to scale up and (re)train the model to improve its accuracy. Evaluated on six representative in-vehicle scenarios, comparative experiments against eleven state-of-the-art techniques show that ConvertNet achieves as much as 22.33% improvement in learning accuracy, and reduces energy consumption by 3.65x.

The negative impact of label noise is well studied in classical supervised learning yet remains an open research question in meta-learning. Meta-learners aim to adapt to unseen tasks by learning a good initial model in meta-training and fine-tuning it to new tasks during meta-testing. In this paper, we present an extensive analysis of the impact of label noise on the performance of meta-learners, specifically gradient-based N-way K-shot learners. We show that the accuracy of Reptile, iMAML, and foMAML drops by up to 34% when meta-training is affected by label noise on the three representative datasets: Omniglot, CifarFS, and MiniImageNet. To strengthen the resilience against label noise, we propose two sampling techniques, namely manifold (Man) and batch manifold (BatMan), which transforms the noisy supervised learners into semi-supervised learners to increase the utility of noisy labels. We construct N-way 2-contrastive-shot tasks through augmentation, learn the embedding via a contrastive loss in meta-training, and perform classification through zeroing on the embeddings in meta-testing. We show that our approach can effectively mitigate the impact of meta-training label noise. Even with 60% wrong labels BatMan and Man can limit the meta-testing accuracy drop to 2.5, 9.4, 1.1% points with existing meta-learners across Omniglot, CifarFS, and MiniImageNet, respectively. We provide our code online: https://gitlab.ewi.tudelft.nl/dmls/publications/batman-clr-noisy-meta-learning.

Effective large-scale process optimization in manufacturing industries requires close cooperation between different human expert parties who encode their knowledge of related domains as Bayesian network models. For instance, Bayesian networks for domains such as lithography equipment, processes, and auxiliary tools must be conjointly used to effectively identify process optimizations in the semiconductor industry. However, business confidentiality across domains hinders such collaboration, and encourages alternatives to centralized inference. We propose CCBNet, the first Confidentiality-preserving Collaborative Bayesian Networks inference framework. CCBNet leverages secret sharing to securely perform analysis on the combined knowledge of party models by joining two novel subprotocols: (i) CABN, which augments probability distributions for variables across parties by modeling them into secret shares of their normalized combination; and (ii) SAVE, which aggregates party inference result shares through distributed variable elimination. We extensively evaluate CCBNet via 9 public Bayesian networks. Our results show that CCBNet achieves predictive quality that is similar to the ones of centralized methods while preserving model confidentiality. We further demonstrate that CCBNet scales to challenging manufacturing use cases that involve 16–128 parties in large networks of 223–1003 variables, and decreases, on average, computational overhead by 23%, while communicating 71k values per request. Finally, we showcase possible attacks and mitigations for partially reconstructing party networks in the protocol.

While diffusion models effectively generate remarkable synthetic images, a key limitation is the inference inefficiency, requiring numerous sampling steps. To accelerate inference and maintain high-quality synthesis, teacher-student distillation is applied to compress the diffusion models in a progressive and binary manner by retraining, e.g., reducing the 1024-step model to a 128-step model in 3 folds. In this paper, we propose a single-fold distillation algorithm, SFDDM, which can flexibly compress the teacher diffusion model into a student model of any desired step, based on reparameterization of the intermediate inputs from the teacher model. To train the student diffusion, we minimize not only the output distance but also the distribution of the hidden variables between the teacher and student model. Extensive experiments on four datasets demonstrate that our student model trained by the proposed SFDDM is able to sample high-quality data with steps reduced to less than 1%, thus, trading off inference time. Our remarkable performance highlights that SFDDM effectively transfers knowledge in single-fold distillation, achieving semantic consistency and meaningful image interpolation.

Federated Learning (FL) systems evolve in heterogeneous and ever-evolving environments that challenge their performance. Under real deployments, the learning tasks of clients can also evolve with time, which calls for the integration of methodologies such as Continual Learning (CL). To enable research reproducibility, we propose a set of experimental best practices that precisely capture and emulate complex learning scenarios. To the best of our knowledge, our framework, Freddie, is the first entirely configurable framework for Federated Continual Learning (FCL), and it can be seamlessly deployed on a large number of machines leveraging containerization and Kubernetes. We demonstrate the effectiveness of Freddie on two use cases, (i) large-scale concurrent FL on CIFAR100 and (ii) heterogeneous task sequence on FCL, which highlight unaddressed performance challenges in FCL scenarios.

When running edge intelligence applications with 6G networks, model pipeline effectively reduces inference latency via parallelizing layers across multiple edge devices. Today’s edge inference systems usually employ static architecture of layers in pipeline parallelism but dynamically skip part of layers in early-exit, which may significantly degrade system throughput. In this paper, we introduce DensePipe, an online layer scheduling approach that optimally allocates early-exit layers to edge devices to maximize their throughput in model pipeline. To this end, DensePipe profiles all network layers’ skipping probabilities in early-exit. At run-time, DensePipe maximizes the pipeline throughput by balancing the processing of all unskipped layers among devices according to the current loads and device resource utilizations. We implement DensePipe with Transformer models and demonstrate its effectiveness against state-of-the-art pipeline methods. Comparative experiments show that DensePiple successfully finds the best devices for most of the layers and significantly improves throughput by 3.09x.

Edge applications are increasingly empowered by deep neural networks (DNN) and face the challenges of adapting or retraining models for the changes in input data domains and learning tasks. The existing techniques to enable DNN retraining on edge devices are to configure the memory-related hyperparameters, termed m-hyperparameters, via batch size reduction, parameter freezing, and gradient checkpoint. While those methods show promising results for static DNNs, little is known about how to online and opportunistically optimize all their m-hyperparameters, especially for retraining tasks of edge applications. In this paper, we propose, MPOptimizer, which jointly optimizes an ensemble of m-hyperparameters according to the input distribution and available edge resources at runtime. The key feature of MPOptimizer is to easily emulate the execution of retraining tasks under different m-hyperparameters and thus effectively estimate their influence on task performance. We implement MPOptimizer on prevalent DNNs and demonstrate its effectiveness against state-of-the-art techniques, i.e. successfully find the best configuration that improves model accuracy by an average of 13% (up to 25.3%) while reducing memory and training time by 4.1x and 5.3x under the same model accuracies.

Diffusion models are becoming the most prevalent generative models, producing exceptional high-quality image data through a stochastic process of diffusion steps based on Gaussian noises. Recent studies explore the federated training of diffusion models, enabling the collaborative training of a model without clients sharing raw data. We demonstrate that even without direct sharing of the data, the shared gradients of federated diffusion models already leak sensitive information about the raw data. We design the first gradient inversion attack GIDM for diffusion, which can reconstruct the training data from the shared model updates. GIDM is a two-phase fusion attack that is both efficient and effective. In its first phase, GIDM leverages the trained diffusion model itself as prior knowledge to constrain the inversion search (latent) space, followed by a second phase of pixel-wise fine-tuning. Different from existing inversion attacks on the classification models, inverting diffusion models present new challenges, most notably that the noise term and randomly sampled diffusion step are not known to the attacker but are required for the reconstruction. To tackle this challenge, we propose a joint triple-optimization algorithm to approximate the raw data, sampling step, and noise term simultaneously. GIDM is shown to be able to reconstruct images almost identical to the original ones and clearly outperforms baselines, i.e., GIDM without the second phase and state-of-the-art attacks on classifiers adapted to diffusion. The code of our method is available at https://github.com/GillHuang-Xtler/Diffusion_inversion.

Federated continual learning (FCL) has attracted growing attention in achieving collaborative model training among edge clients, each of which learns its local model for a sequence of tasks. Most existing FCL approaches aggregate clients' latest local models to exchange knowledge. This unfortunately deviates from real-world scenarios where each model is optimized independently using the client's own dynamic data and different clients have heterogeneous tasks. These tasks not only have distinct class labels (e.g. animals or vehicles) but also differ in input feature distributions. The aggregated model thus often shifts to a higher loss value and incurs accuracy degradation. In this paper, we depart from the model-grained view of aggregation and transform it into multiple task-grained aggregations. Each aggregation allows a client to learn from other clients to improve its model accuracy on one task. To this end, we propose Loci to provide abstractions for clients' past and peer task knowledge using compact model weights, and develop a communication-efficient approach to train each client's local model by exchanging its tasks' knowledge with the most accuracy relevant one from other clients. Through its general-purpose API, Loci can be used to provide efficient on-device training for existing deep learning applications of graph, image, nature language processing, and multimodal data. Using extensive comparative evaluations, we show Loci improves the model accuracy by 32.48% without increasing training time, reduces communication cost by 83.6%, and achieves more improvements when scale (task/client number) increases.

Foundation models (FMs) such as large language models are becoming the backbone technology for artificial intelligence systems. It is particularly challenging to deploy multiple FMs on edge devices, which not only have limited computational resources, but also encounter unseen input data from evolving domains or learning tasks. When new data arrives, existing prior art of FM mainly focuses on retraining compressed models of predetermined network architectures, limiting the feasibility of edge devices to efficiently achieve high accuracy for FMs. In this paper, we propose EdgeTA, a neuron-grained FM scaling system to maximize the overall accuracy of FMs promptly in response to their data dynamics. EdgeTA's key design features in scaling are (i) proxy mechanism, which adaptively transforms a FM into a compact architecture retaining the most important neurons to the input data, and (ii) neuron-grained scheduler, which jointly optimizes model sizes and resource allocation for all FMs on edge devices. Under tight retraining window and limited device resources, the design of EdgeTA can achieve most of the original FM's accuracy with much smaller retraining costs. We implement EdgeTA on FMs of natural language processing, computer vision and multimodal applications. Comparison results against state-of-the-art techniques show that our approach improves accuracy by 21.88% and reduces memory footprint and energy consumptions by 27.14% and 65.65%, while further achieving 15.96% overall accuracy improvement via neuron-grained scheduling.

Shareable tabular data is of high importance in industry and research. While generating synthetic records is well-studied, research has only recently extended to relational data synthesis. In the tabular generation setting, diffusion and transformer models exhibit superior performance over prior art. However, in the relational setting, diffusion models outperform transformers. This work focuses on the performance gap between tabular transformers and diffusion models in single (tabular) and multi-table (relational) settings, using REaLTabformer and ClavaDDPM as representative state-of-the-art models. We evaluate these architectures on a set of single- and multi-table datasets, highlighting the gap's root causes between the methods. In our experiments, we attribute this difference to the influence of contextual information and data representation. To bridge the gap in the relational setting, we propose two seemingly simple strategies: layer sharing and contextual cues. This work1 offers insights into key design considerations for single- and multitable generative models, including the incorporation of contextual information and the reuse of existing knowledge. With the proposed methods, we achieve improvements of 1.52× and 1.94× for the Logistic Detection and Discriminator Measure metrics, respectively.

AI applications powered by deep learning models are increasingly run natively at edge. A deployed model not only encounters continuously evolving input distributions (domains) but also faces adversarial attacks from third-party. This necessitates adapting the model to shifting domains to maintain high natural accuracy, while avoiding degrading the model's robust accuracy. However, existing domain adaptation and adversarial attack preventation techniques often have conflicting optimization objectives and they rely on time-consuming training process. This paper presents RobustDA, an on-device lightweight approach that co-optimizes natural and robust accuracies in model retraining. It uses a set of low-rank adapters to retain all learned domains' knowledge with small overheads. In each model retraining, RobustDA constructs an adapter to separate domain-related and robust-related model parameters to avoid their conflicts in updating. Based on the retained knowledge, it quickly generates adversarial examples with high-quality pseudo-labels and uses them to accelerate the retraining process. We demonstrate that, comparing against 14 state-of-the-art DA techniques under 7 prevalent adversarial attacks on edge devices, the proposed co-optimization approach improves natural and robust accuracies by 6.34% and 11.41% simultaneously. Under the same accuracy, RobustDA also speeds up the retraining process by 4.09x.

Synthetic tabular data is crucial for sharing and augmenting data across silos, especially for enterprises with proprietary data. However, existing synthesizers are designed for centrally stored data. Hence, they struggle with real-world scenarios where features are distributed across multiple silos, necessitating on-premise data storage. We introduce SiloFuse, a novel generative framework for high-quality synthesis from cross-silo tabular data. To ensure privacy, SiloFuse utilizes a distributed latent tabular diffusion architecture. Through autoencoders, latent representations are learned for each client's features, masking their actual values. We employ stacked dis-tributed training to improve communication efficiency, reducing the number of rounds to a single step. Under SiloFuse, we prove the impossibility of data reconstruction for vertically partitioned synthesis and quantify privacy risks through three attacks using our benchmark framework. Experimental results on nine datasets showcase SiloFuse's competence against centralized diffusion-based synthesizers. Notably, SiloFuse achieves 43.8 and 29.8 higher percentage points over GANs in resemblance and utility. Experiments on communication show stacked training's fixed cost compared to the growing costs of end-to-end training as the number of training iterations increases. Additionally, SiloFuse proves robust to feature permutations and varying numbers of clients.

Executing deep neural networks (DNN) based vision tasks on edge devices encounters challenging scenarios of significant and continually evolving data domains (e.g. background or subpopulation shift). With limited resources, the state-of-the-art domain adaptation (DA) methods either cause high training overheads on large DNN models, or incur significant accuracy losses when adapting small/compressed models in an online fashion. The inefficient resource scheduling among multiple applications further degrades their overall model accuracy. In this paper, we present ElasticDNN, a framework that enables online DNN remodeling for applications encountering evolving domain drifts at edge. Its first key component is the master-surrogate DNN models, which can dynamically generate a small surrogate DNN by retaining and training the large master DNN's most relevant regions pertinent to the new domain. The second novelty of ElasticDNN is the filter-grained resource scheduling, which allocates GPU resources based on online accuracy estimation and DNN remodeling of co-running applications. We fully implement ElasticDNN and demonstrate its effectiveness through extensive experiments. The results show that, compared to existing online DA methods using the same model sizes, ElasticDNN improves accuracy by 23.31% and reduces adaption time by 35.67x. In the more challenging multi-application scenario, ElasticDNN improves accuracy by an average of 25.91%.

Federated learning (FL) systems enable multiple clients to train a machine learning model iteratively through synchronously exchanging the intermediate model weights with a single server. The scalability of such FL systems can be limited by two factors: server idle time due to synchronous communication and the risk of a single server becoming the bottleneck. In this paper, we propose a new FL architecture, Spyker, the first multi-server FL system that is entirely asynchronous, and therefore addresses these two limitations simultaneously. Spyker keeps both servers and clients continuously active. As in previous multi-server methods, clients interact solely with their nearest server, ensuring efficient update integration into the model. Differently, however, servers also periodically update each other asynchronously, and never postpone interactions with clients. We compare Spyker to three representative baselines - FedAvg, FedAsync and HierFAVG - on the MNIST and CIFAR-10 image classification datasets and on the WikiText-2 language modeling dataset. Spyker converges to similar or higher accuracy levels than previous baselines and requires 61% less time to do so in geo-distributed settings.

Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral part of our daily life. When tackling the evolving learning tasks in real world, such as classifying different types of objects, DNNs face the challenge to continually retrain themselves according to the tasks on different edge devices. Federated continual learning (FCL) is a promising technique that offers partial solutions but yet to overcome the following difficulties: the significant accuracy loss due to the limited on-device processing, the negative knowledge transfer caused by the limited communication of non-IID (non-Independent and Identically Distributed) data, and the limited scalability on the tasks and edge devices. Moreover, existing FCL techniques are designed for convolutional neural networks (CNNs), which have not utilized the full potential of newly emerged powerful vision transformers (ViTs). Considering ViTs depend heavily on training data diversity and volume, we hypothesize ViTs are well-suited for FCL where data arrives continually. In this paper, we propose FedViT, an accurate and scalable federated continual learning framework for ViT models, via a novel concept of signature task knowledge. FedViT is a client-side solution that continuously extracts and integrates the knowledge of signature tasks which are highly influenced by the current task. Each client of FedViT is composed of a knowledge extractor, a gradient restorer and, most importantly, a gradient integrator. Upon training for a new task, the gradient integrator ensures the prevention of catastrophic forgetting and mitigation of negative knowledge transfer by effectively combining signature tasks identified from the past local tasks and other clients’ current tasks through the global model. We implement FedViT in PyTorch and extensively evaluate it against state-of-the-art techniques using popular federated continual learning benchmarks. Extensive evaluation results on heterogeneous edge devices show that FedViT improves model accuracy by 88.61% without increasing model training time, reduces communication cost by 61.55%, and achieves more improvements under difficult scenarios such as large numbers of tasks or clients, and training different complex ViT models.

Machine learning (ML) training data is often scattered across disparate collections of datasets, called <italic>data silos</italic>. This fragmentation poses a major challenge for data-intensive ML applications: integrating and transforming data residing in different sources demand a lot of manual work and computational resources. With data privacy constraints, data often cannot leave the premises of data silos; hence model training should proceed in a decentralized manner. In this work, we present a vision of bridging traditional data integration (DI) techniques with the requirements of modern machine learning systems. We explore the possibilities of utilizing metadata obtained from data integration processes for improving the effectiveness, efficiency, and privacy of ML models. Towards this direction, we analyze ML training and inference over data silos. Bringing data integration and machine learning together, we highlight new research opportunities from the aspects of systems, representations, factorized learning, and federated learning.

In a decade, AI frontier research transitioned from the researcher's workstation to thousands of high-end hardware-accelerated compute nodes. This rapid evolution shows no signs of slowing down in the foreseeable future. While top cloud providers may be able to keep pace with this growth rate, obtaining and efficiently exploiting computing resources at that scale is a daunting challenge for universities and SMEs. This work introduces the Cross-Facility Federated Learning (XFFL) framework to bridge this compute divide, extending the opportunity to efficiently exploit multiple independent data centres for extreme-scale deep learning tasks to data scientists and domain experts. XFFL relies on hybrid workflow abstractions to decouple tasks from environment-specific technicalities, reducing complexity and enhancing reusability. In addition, Federated Learning (FL) algorithms eliminate the need to move large amounts of data between different facilities, reducing time-to-solution and preserving data privacy. The XFFL approach is empirically evaluated by training a full LLaMAv2 7B instance on two facilities of the EuroHPC JU, showing how the increased computing power completely compensates for the additional overhead introduced by two data centres.

Generative Adversarial Networks (GANs) are increasingly adopted by the industry to synthesize realistic images using competing generator and discriminator neural networks. Due to data not being centrally available, Multi-Discriminator (MD)-GANs training frameworks employ multiple discriminators that have direct access to the real data. Distributedly training a joint GAN model entails the risk of free-riders, i.e., participants that aim to benefit from the common model while only pretending to participate in the training process. In this paper, we first define a free-rider as a participant without training data and then identify three possible actions: not training, training on synthetic data, or using pre-trained models for similar but not identical tasks that are publicly available. We conduct experiments to explore the impact of these three types of free-riders on the ability of MD-GANs to produce images that are indistinguishable from real data. We consequently design a defense against free-riders, termed DFG, which compares the performance of client discriminators to reference discriminators at the server. The defense allows the server to evict clients whose behavior does not match that of a benign client. The result shows that even when 67% of the clients are free-riders, the proposed DFG can improve synthetic image quality by up to 70.96%, compared to the case of no defense.