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.

With the growing volume of Internet of Things (IoT) data acquired in edge-side visual recognition applications, peer-to-peer decentralized federated learning (DFL) has emerged as an attractive model training paradigm. Unlike centralized FL where a server aggregates per-round client updates, DFL clients directly exchange sparsified model parameters (only a subset is transmitted each round). The exchanged parameters embed accumulated training history rather than independent round updates. This creates a fundamental dilemma for privacy protection with differential privacy (DP): to prevent historical leakage, existing methods are forced to update only the small fraction (e.g., 10%) of parameters currently being exchanged and protected by DP noise, leaving most parameters frozen and severely degrading accuracy. In this paper, we propose DecentDP, an approach that addresses this dilemma to improve model accuracy. The two key modules of DecentDP are: (i) a parameter selector that designates a subset of parameters for local-only updates, allowing them to be updated without DP noise; and (ii) a noise injector that adaptively adds less DP noise to exchangeable parameters that are more sensitive to DP noise. Experiments across five settings show that DecentDP outperforms 11 baselines, achieving an average accuracy improvement of 15.68%, with only 0.70% additional computational overhead and 0.60% additional communication overhead.

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.

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.

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.

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.

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.

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.