The Federated Learning (FL) paradigm is known to face challenges under heterogeneous client data. Local training on non-iid distributed data results in deflected local optimum, which causes the client models drift further away from each other and degrades the aggregated global model's performance. A natural solution is to gather all client data onto the server, such that the server has a global view of the entire data distribution. Unfortunately, this reduces to regular training, which compromises clients' privacy and conflicts with the purpose of FL. In this paper, we put forth an idea to collect and leverage global knowledge on the server without hindering data privacy. We unearth such knowledge from the dynamics of the global model's trajectory. Specifically, we first reserve a short trajectory of global model snapshots on the server. Then, we synthesize a small pseudo dataset such that the model trained on it mimics the dynamics of the reserved global model trajectory. Afterward, the synthesized data is used to help aggregate the deflected clients into the global model. We name our method Dynafed, which enjoys the following advantages: 1) we do not rely on any external on-server dataset, which requires no additional cost for data collection; 2) the pseudo data can be synthesized in early communication rounds, which enables Dynafed to take effect early for boosting the convergence and stabilizing training; 3) the pseudo data only needs to be synthesized once and can be directly utilized on the server to help aggregation in subsequent rounds. Experiments across extensive benchmarks are conducted to showcase the effectiveness of Dynafed. We also provide insights and understanding of the underlying mechanism of our method.

Graph contrastive learning (GCL) emerges as the most representative approach for graph representation learning, which leverages the principle of maximizing mutual information (InfoMax) to learn node representations applied in downstream tasks. To explore better generalization from GCL to downstream tasks, previous methods heuristically define data augmentation or pretext tasks. However, the generalization ability of GCL and its theoretical principle are still less reported. In this paper, we first propose a metric named GCL-GE for GCL generalization ability. Considering the intractability of the metric due to the agnostic downstream task, we theoretically prove a mutual information upper bound for it from an information-theoretic perspective. Guided by the bound, we design a GCL framework named InfoAdv with enhanced generalization ability, which jointly optimizes the generalization metric and InfoMax to strike the right balance between pretext task fitting and the generalization ability on downstream tasks. We empirically validate our theoretical findings on a number of representative benchmarks, and experimental results demonstrate that our model achieves state-of-the-art performance.

We show that Contrastive Learning (CL) under a broad family of loss functions (including InfoNCE) has a unified formulation of coordinate-wise optimization on the network parameter $\boldsymbol{\theta}$ and pairwise importance $\alpha$, where the \emph{max player} $\boldsymbol{\theta}$ learns representation for contrastiveness, and the \emph{min player} $\alpha$ puts more weights on pairs of distinct samples that share similar representations. The resulting formulation, called $\alpha$-CL, unifies not only various existing contrastive losses, which differ by how sample-pair importance $\alpha$ is constructed, but also is able to extrapolate to give novel contrastive losses beyond popular ones, opening a new avenue of contrastive loss design. These novel losses yield comparable (or better) performance on CIFAR10, STL-10 and CIFAR-100 than classic InfoNCE. Furthermore, we also analyze the max player in detail: we prove that with fixed $\alpha$, max player is equivalent to Principal Component Analysis (PCA) for deep linear network, and almost all local minima are global and rank-1, recovering optimal PCA solutions. Finally, we extend our analysis on max player to 2-layer ReLU networks, showing that its fixed points can have higher ranks.

Understanding the fundamental mechanism behind the success of transformer networks is still an open problem in the deep learning literature. Although their remarkable performance has been mostly attributed to the self-attention mechanism, the literature still lacks a solid analysis of these networks and interpretation of the functions learned by them. To this end, we study the training problem of attention/transformer networks and introduce a novel convex analytic approach to improve the understanding and optimization of these networks. Particularly, we first introduce a convex alternative to the self-attention mechanism and reformulate the regularized training problem of transformer networks with our alternative convex attention. Then, we cast the reformulation as a convex optimization problem that is interpretable and easier to optimize. Moreover, as a byproduct of our convex analysis, we reveal an implicit regularization mechanism, which promotes sparsity across tokens. Therefore, we not only improve the optimization of attention/transformer networks but also provide a solid theoretical understanding of the functions learned by them. We also demonstrate the effectiveness of our theory through several numerical experiments.

Here I would like to provide some useful machine-learning algorithms you should know. Machine learning is a branch of Artificial Intelligence that enables computers to learn and make predictions based on data. Traditional AI focuses on programming computers to perform specific tasks, such as playing chess or recognizing faces. Machine learning is about giving computers the ability to learn new things and solve new problems without being explicitly programmed. If you are reading this article, you might be one of those curious souls who asks'what if' questions and likes puzzles.

Linear regression is a simple machine learning model and chances are you are already aware of it! Do you remember plotting the line y mx c in your introductory algebra class? This is an equation of a straight line where m is its gradient and c is the point where the line crosses the y-axis. Using this equation, you're able to estimate the value of y for any given value of x. Similarly, linear regression involves estimating the relationship between independent variables (x) and a dependent variable(y).

Getting into the dynamic field of data science requires you to catch up and build on the trends of the industry. Building your portfolio is the right direction for it and solving the existing problems that can orchestrate breakthroughs in the industry is the perfect path to take. Finding the right project that fits your knowledge, matches with requirements of the industry, and gives you real world practical experience is a decision-heavy task. We have compiled a list of trending data science projects that you can explore to help refine your resume and land a job of your choice in 2023! For natural language processing, this data science project involves determining whether the data inferred is positive, negative, or neutral.

Markov Chain Monte Carlo (MCMC) methods are the workhorse of Bayesian computation when closed formulas for estimators or probability distributions are not available. For this reason they have been central to the development and success of high-dimensional Bayesian statistics in the last decades, where one attempts to generate samples from some posterior distribution Π( |data) arising from a prior Π on D-dimensional Euclidean space and the observed data vector. MCMC methods tend to perform well in a large variety of problems, are very flexible and user-friendly, and enjoy many theoretical guarantees. Under mild assumptions, they are known to converge to their stationary'target' distributions as a consequence of the ergodic theorem, albeit perhaps at a slow speed, requiring a large number of iterations to provide numerically accurate algorithms. When the target distribution is log-concave, MCMC algorithms are known to mix rapidly, even in high dimensions.

This paper proposes a Decentralized Stochastic Gradient Descent (DSGD) algorithm to solve distributed machine-learning tasks over wirelessly-connected systems, without the coordination of a base station. It combines local stochastic gradient descent steps with a Non-Coherent Over-The-Air (NCOTA) consensus scheme at the receivers, that enables concurrent transmissions by leveraging the waveform superposition properties of the wireless channels. With NCOTA, local optimization signals are mapped to a mixture of orthogonal preamble sequences and transmitted concurrently over the wireless channel under half-duplex constraints. Consensus is estimated by non-coherently combining the received signals with the preamble sequences and mitigating the impact of noise and fading via a consensus stepsize. NCOTA-DSGD operates without channel state information (typically used in over-the-air computation schemes for channel inversion) and leverages the channel pathloss to mix signals, without explicit knowledge of the mixing weights (typically known in consensus-based optimization). It is shown that, with a suitable tuning of decreasing consensus and learning stepsizes, the error (measured as Euclidean distance) between the local and globally optimum models vanishes with rate $\mathcal O(k^{-1/4})$ after $k$ iterations. NCOTA-DSGD is evaluated numerically by solving an image classification task on the MNIST dataset, cast as a regularized cross-entropy loss minimization. Numerical results depict faster convergence vis-\`a-vis running time than implementations of the classical DSGD algorithm over digital and analog orthogonal channels, when the number of learning devices is large, under stringent delay constraints.

Stochastic differential equations (SDEs) have been shown recently to well characterize the dynamics of training machine learning models with SGD. This provides two opportunities for better understanding the generalization behaviour of SGD through its SDE approximation. First, under the SDE characterization, SGD may be regarded as the full-batch gradient descent with Gaussian gradient noise. This allows the application of the generalization bounds developed by Xu & Raginsky (2017) to analyzing the generalization behaviour of SGD, resulting in upper bounds in terms of the mutual information between the training set and the training trajectory. Second, under mild assumptions, it is possible to obtain an estimate of the steady-state weight distribution of SDE. Using this estimate, we apply the PAC-Bayes-like information-theoretic bounds developed in both Xu & Raginsky (2017) and Negrea et al. (2019) to obtain generalization upper bounds in terms of the KL divergence between the steady-state weight distribution of SGD with respect to a prior distribution. Among various options, one may choose the prior as the steady-state weight distribution obtained by SGD on the same training set but with one example held out. In this case, the bound can be elegantly expressed using the influence function (Koh & Liang, 2017), which suggests that the generalization of the SGD is related to the stability of SGD. Various insights are presented along the development of these bounds, which are subsequently validated numerically.