Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information transferred from the labeled dataset. The unlabeled dataset comprises both known and novel classes. The main challenge is that unlabeled novel class samples and unlabeled known class samples are mixed together in the unlabeled dataset. To address the GCD without knowing the class number of unlabeled dataset, we propose a co-training-based framework that encourages clustering consistency. Specifically, we first introduce weak and strong augmentation transformations to generate two sufficiently different views for the same sample. Then, based on the co-training assumption, we propose a consistency representation learning strategy, which encourages consistency between feature-prototype similarity and clustering assignment. Finally, we use the discriminative embeddings learned from the semi-supervised representation learning process to construct an original sparse network and use a community detection method to obtain the clustering results and the number of categories simultaneously. Extensive experiments show that our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets. Especially in the ImageNet-100 data set, our method significantly exceeds the best baseline by 15.5\% and 7.0\% on the \texttt{Novel} and \texttt{All} classes, respectively.
With the rapid growth of edge intelligence, the deployment of federated learning (FL) over wireless networks has garnered increasing attention, which is called Federated Edge Learning (FEEL). In FEEL, both mobile devices transmitting model parameters over noisy channels and collecting data in diverse environments pose challenges to the generalization of trained models. Moreover, devices can engage in decentralized FL via Device-to-Device communication while the communication topology of connected devices also impacts the generalization of models. Most recent theoretical studies overlook the incorporation of all these effects into FEEL when developing generalization analyses. In contrast, our work presents an information-theoretic generalization analysis for topology-aware FEEL in the presence of data heterogeneity and noisy channels. Additionally, we propose a novel regularization method called Federated Global Mutual Information Reduction (FedGMIR) to enhance the performance of models based on our analysis. Numerical results validate our theoretical findings and provide evidence for the effectiveness of the proposed method.
Training large models from scratch usually costs a substantial amount of resources. Towards this problem, recent studies such as bert2BERT and LiGO have reused small pretrained models to initialize a large model (termed the ``target model''), leading to a considerable acceleration in training. Despite the successes of these previous studies, they grew pretrained models by mapping partial weights only, ignoring potential correlations across the entire model. As we show in this paper, there are inter- and intra-interactions among the weights of both the pretrained and the target models. As a result, the partial mapping may not capture the complete information and lead to inadequate growth. In this paper, we propose a method that linearly correlates each weight of the target model to all the weights of the pretrained model to further enhance acceleration ability. We utilize multi-linear operators to reduce computational and spacial complexity, enabling acceptable resource requirements. Experiments demonstrate that our method can save 76\% computational costs on DeiT-base transferred from DeiT-small, which outperforms bert2BERT by +12.0\% and LiGO by +20.7\%, respectively.
Federated Learning (FL) has surged in prominence due to its capability of collaborative model training without direct data sharing. However, the vast disparity in local data distributions among clients, often termed the non-Independent Identically Distributed (non-IID) challenge, poses a significant hurdle to FL's generalization efficacy. The scenario becomes even more complex when not all clients participate in the training process, a common occurrence due to unstable network connections or limited computational capacities. This can greatly complicate the assessment of the trained models' generalization abilities. While a plethora of recent studies has centered on the generalization gap pertaining to unseen data from participating clients with diverse distributions, the divergence between the training distributions of participating clients and the testing distributions of non-participating ones has been largely overlooked. In response, our paper unveils an information-theoretic generalization framework for FL. Specifically, it quantifies generalization errors by evaluating the information entropy of local distributions and discerning discrepancies across these distributions. Inspired by our deduced generalization bounds, we introduce a weighted aggregation approach and a duo of client selection strategies. These innovations aim to bolster FL's generalization prowess by encompassing a more varied set of client data distributions. Our extensive empirical evaluations reaffirm the potency of our proposed methods, aligning seamlessly with our theoretical construct.
Transferring a pretrained model to a downstream task can be as easy as conducting linear probing with target data, that is, training a linear classifier upon frozen features extracted from the pretrained model. As there may exist significant gaps between pretraining and downstream datasets, one may ask whether all dimensions of the pretrained features are useful for a given downstream task. We show that, for linear probing, the pretrained features can be extremely redundant when the downstream data is scarce, or few-shot. For some cases such as 5-way 1-shot tasks, using only 1\% of the most important feature dimensions is able to recover the performance achieved by using the full representation. Interestingly, most dimensions are redundant only under few-shot settings and gradually become useful when the number of shots increases, suggesting that feature redundancy may be the key to characterizing the "few-shot" nature of few-shot transfer problems. We give a theoretical understanding of this phenomenon and show how dimensions with high variance and small distance between class centroids can serve as confounding factors that severely disturb classification results under few-shot settings. As an attempt at solving this problem, we find that the redundant features are difficult to identify accurately with a small number of training samples, but we can instead adjust feature magnitude with a soft mask based on estimated feature importance. We show that this method can generally improve few-shot transfer performance across various pretrained models and downstream datasets.
Federated learning refers to a distributed machine learning paradigm in which data samples are decentralized and distributed among multiple clients. These samples may exhibit statistical heterogeneity, which refers to data distributions are not independent and identical across clients. Additionally, system heterogeneity, or variations in the computational power of the clients, introduces biases into federated learning. The combined effects of statistical and system heterogeneity can significantly reduce the efficiency of federated optimization. However, the impact of hybrid heterogeneity is not rigorously discussed. This paper explores how hybrid heterogeneity affects federated optimization by investigating server-side optimization. The theoretical results indicate that adaptively maximizing gradient diversity in server update direction can help mitigate the potential negative consequences of hybrid heterogeneity. To this end, we introduce a novel server-side gradient-based optimizer \textsc{FedAWARE} with theoretical guarantees provided. Intensive experiments in heterogeneous federated settings demonstrate that our proposed optimizer can significantly enhance the performance of federated learning across varying degrees of hybrid heterogeneity.
Federated Learning (FL) systems usually sample a fraction of clients to conduct a training process. Notably, the variance of global estimates for updating the global model built on information from sampled clients is highly related to federated optimization quality. This paper explores a line of "free" adaptive client sampling techniques in federated optimization, where the server builds promising sampling probability and reliable global estimates without requiring additional local communication and computation. We capture a minor variant in the sampling procedure and improve the global estimation accordingly. Based on that, we propose a novel sampler called K-Vib, which solves an online convex optimization respecting client sampling in federated optimization. It achieves improved a linear speed up on regret bound $\tilde{\mathcal{O}}\big(N^{\frac{1}{3}}T^{\frac{2}{3}}/K^{\frac{4}{3}}\big)$ with communication budget $K$. As a result, it significantly improves the performance of federated optimization. Theoretical improvements and intensive experiments on classic federated tasks demonstrate our findings.
Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data. However, the presence of statistical heterogeneity among clients poses a challenge, as the global model may struggle to perform well on each client's specific task. To address this issue, we introduce a new perspective on personalized federated learning through Amortized Bayesian Meta-Learning. Specifically, we propose a novel algorithm called \emph{FedABML}, which employs hierarchical variational inference across clients. The global prior aims to capture representations of common intrinsic structures from heterogeneous clients, which can then be transferred to their respective tasks and aid in the generation of accurate client-specific approximate posteriors through a few local updates. Our theoretical analysis provides an upper bound on the average generalization error and guarantees the generalization performance on unseen data. Finally, several empirical results are implemented to demonstrate that \emph{FedABML} outperforms several competitive baselines.
Gaussian process regression (GPR) is a non-parametric model that has been used in many real-world applications that involve sensitive personal data (e.g., healthcare, finance, etc.) from multiple data owners. To fully and securely exploit the value of different data sources, this paper proposes a privacy-preserving GPR method based on secret sharing (SS), a secure multi-party computation (SMPC) technique. In contrast to existing studies that protect the data privacy of GPR via homomorphic encryption, differential privacy, or federated learning, our proposed method is more practical and can be used to preserve the data privacy of both the model inputs and outputs for various data-sharing scenarios (e.g., horizontally/vertically-partitioned data). However, it is non-trivial to directly apply SS on the conventional GPR algorithm, as it includes some operations whose accuracy and/or efficiency have not been well-enhanced in the current SMPC protocol. To address this issue, we derive a new SS-based exponentiation operation through the idea of 'confusion-correction' and construct an SS-based matrix inversion algorithm based on Cholesky decomposition. More importantly, we theoretically analyze the communication cost and the security of the proposed SS-based operations. Empirical results show that our proposed method can achieve reasonable accuracy and efficiency under the premise of preserving data privacy.