Federated learning typically considers collaboratively training a global model using local data at edge clients. Clients may have their own individual requirements, such as having a minimal training loss threshold, which they expect to be met by the global model. However, due to client heterogeneity, the global model may not meet each client's requirements, and only a small subset may find the global model appealing. In this work, we explore the problem of the global model lacking appeal to the clients due to not being able to satisfy local requirements. We propose MaxFL, which aims to maximize the number of clients that find the global model appealing. We show that having a high global model appeal is important to maintain an adequate pool of clients for training, and can directly improve the test accuracy on both seen and unseen clients. We provide convergence guarantees for MaxFL and show that MaxFL achieves a $22$-$40\%$ and $18$-$50\%$ test accuracy improvement for the training clients and unseen clients respectively, compared to a wide range of FL modeling approaches, including those that tackle data heterogeneity, aim to incentivize clients, and learn personalized or fair models.

Identifying abnormal patterns in electroencephalography (EEG) remains the cornerstone of diagnosing several neurological diseases. The current clinical EEG review process relies heavily on expert visual review, which is unscalable and error-prone. In an effort to augment the expert review process, there is a significant interest in mining population-level EEG patterns using unsupervised approaches. Current approaches rely either on two-dimensional decompositions (e.g., principal and independent component analyses) or deep representation learning (e.g., auto-encoders, self-supervision). However, most approaches do not leverage the natural multi-dimensional structure of EEGs and lack interpretability. In this study, we propose a tensor decomposition approach using the canonical polyadic decomposition to discover a parsimonious set of population-level EEG patterns, retaining the natural multi-dimensional structure of EEGs (time x space x frequency). We then validate their clinical value using a cohort of patients including varying stages of cognitive impairment. Our results show that the discovered patterns reflect physiologically meaningful features and accurately classify the stages of cognitive impairment (healthy vs mild cognitive impairment vs Alzheimer's dementia) with substantially fewer features compared to classical and deep learning-based baselines. We conclude that the decomposition of population-level EEG tensors recovers expert-interpretable EEG patterns that can aid in the study of smaller specialized clinical cohorts.

This paper studies the algorithmic stability and generalizability of decentralized stochastic gradient descent (D-SGD). We prove that the consensus model learned by D-SGD is $\mathcal{O}{(N^{-1}+m^{-1} +\lambda^2)}$-stable in expectation in the non-convex non-smooth setting, where $N$ is the total sample size, $m$ is the worker number, and $1+\lambda$ is the spectral gap that measures the connectivity of the communication topology. These results then deliver an $\mathcal{O}{(N^{-(1+\alpha)/2}+ m^{-(1+\alpha)/2}+\lambda^{1+\alpha} + \phi_{\mathcal{S}})}$ in-average generalization bound, which is non-vacuous even when $\lambda$ is closed to $1$, in contrast to vacuous as suggested by existing literature on the projected version of D-SGD. Our theory indicates that the generalizability of D-SGD is positively correlated with the spectral gap, and can explain why consensus control in initial training phase can ensure better generalization. Experiments of VGG-11 and ResNet-18 on CIFAR-10, CIFAR-100 and Tiny-ImageNet justify our theory. To our best knowledge, this is the first work on the topology-aware generalization of vanilla D-SGD. Code is available at https://github.com/Raiden-Zhu/Generalization-of-DSGD.

Product-related reviews are based on users' experiences that are mostly shared on videos in YouTube. It is the second most popular website globally in 2021. People prefer to watch videos on recently released products prior to purchasing, in order to gather overall feedback and make worthy decisions. These videos are created by vloggers who are enthusiastic about technical materials and feedback is usually placed by experienced users of the product or its brand. Analyzing the sentiment of the user reviews gives useful insights into the product in general. This study is focused on three smartphone reviews, namely, Apple iPhone 13, Google Pixel 6, and Samsung Galaxy S21 which were released in 2021. VADER, which is a lexicon and rule-based sentiment analysis tool was used to classify each comment to its appropriate positive or negative orientation. All three smartphones show a positive sentiment from the users' perspective and iPhone 13 has the highest number of positive reviews. The resulting models have been tested using N\"aive Bayes, Decision Tree, and Support Vector Machine. Among these three classifiers, Support Vector Machine shows higher accuracies and F1-scores.

We propose a learning framework for calibrating predictive models to make loss-controlling prediction for exchangeable data, which extends our recently proposed conformal loss-controlling prediction for more general cases. By comparison, the predictors built by the proposed loss-controlling approach are not limited to set predictors, and the loss function can be any measurable function without the monotone assumption. To control the loss values in an efficient way, we introduce transformations preserving exchangeability to prove finite-sample controlling guarantee when the test label is obtained, and then develop an approximation approach to construct predictors. The transformations can be built on any predefined function, which include using optimization algorithms for parameter searching. This approach is a natural extension of conformal loss-controlling prediction, since it can be reduced to the latter when the set predictors have the nesting property and the loss functions are monotone. Our proposed method is applied to selective regression and high-impact weather forecasting problems, which demonstrates its effectiveness for general loss-controlling prediction.

We propose a paradigm for interpretable Manifold Learning for scientific data analysis, whereby we parametrize a manifold with $d$ smooth functions from a scientist-provided dictionary of meaningful, domain-related functions. When such a parametrization exists, we provide an algorithm for finding it based on sparse non-linear regression in the manifold tangent bundle, bypassing more standard manifold learning algorithms. We also discuss conditions for the existence of such parameterizations in function space and for successful recovery from finite samples. We demonstrate our method with experimental results from a real scientific domain.

Self-organization is ubiquitous in nature and mind. However, machine learning and theories of cognition still barely touch the subject. The hurdle is that general patterns are difficult to define in terms of dynamical equations and designing a system that could learn by reordering itself is still to be seen. Here, we propose a learning system, where patterns are defined within the realm of nonlinear dynamics with positive and negative feedback loops, allowing attractor-repeller pairs to emerge for each pattern observed. Experiments reveal that such a system can map temporal to spatial correlation, enabling hierarchical structures to be learned from sequential data. The results are accurate enough to surpass state-of-the-art unsupervised learning algorithms in seven out of eight experiments as well as two real-world problems. Interestingly, the dynamic nature of the system makes it inherently adaptive, giving rise to phenomena similar to phase transitions in chemistry/thermodynamics when the input structure changes. Thus, the work here sheds light on how self-organization can allow for pattern recognition and hints at how intelligent behavior might emerge from simple dynamic equations without any objective/loss function.

Image search engines enable the retrieval of images relevant to a query image. In this work, we consider the setting where a query for similar images is derived from a collection of images. For visual search, the similarity measurements may be made along multiple axes, or views, such as style and color. We assume access to a set of feature extractors, each of which computes representations for a specific view. Our objective is to design a retrieval algorithm that effectively combines similarities computed over representations from multiple views. To this end, we propose a self-supervised learning method for extracting disentangled view-specific representations for images such that the inter-view overlap is minimized. We show how this allows us to compute the intent of a collection as a distribution over views. We show how effective retrieval can be performed by prioritizing candidate expansion images that match the intent of a query collection. Finally, we present a new querying mechanism for image search enabled by composing multiple collections and perform retrieval under this setting using the techniques presented in this paper.

Clustering in graphs has been a well-known research problem, particularly because most Internet and social network data is in the form of graphs. Organizations widely use spectral clustering algorithms to find clustering in graph datasets. However, applying spectral clustering to a large dataset is challenging due to computational overhead. While the distributed spectral clustering algorithm exists, they face the problem of data privacy and increased communication costs between the clients. Thus, in this paper, we propose a spectral clustering algorithm using federated learning (FL) to overcome these issues. FL is a privacy-protecting algorithm that accumulates model parameters from each local learner rather than collecting users' raw data, thus providing both scalability and data privacy. We developed two approaches: FedSpectral and FedSpectral+. FedSpectral is a baseline approach that uses local spectral clustering labels to aggregate the global spectral clustering by creating a similarity graph. FedSpectral+, a state-of-the-art approach, uses the power iteration method to learn the global spectral embedding by incorporating the entire graph data without access to the raw information distributed among the clients. We further designed our own similarity metric to check the clustering quality of the distributed approach to that of the original/non-FL clustering. The proposed approach FedSpectral+ obtained a similarity of 98.85% and 99.8%, comparable to that of global clustering on the ego-Facebook and email-Eu-core dataset.

The problem of tensor completion has applications in healthcare, computer vision, and other domains. However, past approaches to tensor completion have faced a tension in that they either have polynomial-time computation but require exponentially more samples than the information-theoretic rate, or they use fewer samples but require solving NP-hard problems for which there are no known practical algorithms. A recent approach, based on integer programming, resolves this tension for nonnegative tensor completion. It achieves the information-theoretic sample complexity rate and deploys the Blended Conditional Gradients algorithm, which requires a linear (in numerical tolerance) number of oracle steps to converge to the global optimum. The tradeoff in this approach is that, in the worst case, the oracle step requires solving an integer linear program. Despite this theoretical limitation, numerical experiments show that this algorithm can, on certain instances, scale up to 100 million entries while running on a personal computer. The goal of this paper is to further enhance this algorithm, with the intention to expand both the breadth and scale of instances that can be solved. We explore several variants that can maintain the same theoretical guarantees as the algorithm, but offer potentially faster computation. We consider different data structures, acceleration of gradient descent steps, and the use of the Blended Pairwise Conditional Gradients algorithm. We describe the original approach and these variants, and conduct numerical experiments in order to explore various tradeoffs in these algorithmic design choices.