Machine learning (ML) applications continue to revolutionize many domains. In recent years, there has been considerable research interest in building novel ML applications for a variety of Internet of Things (IoT) domains, such as precision agriculture, smart cities, and smart manufacturing. IoT domains are characterized by continuous streams of data originating from diverse, geographically distributed sensors, and they often require a real-time or semi-real-time response. IoT characteristics pose several fundamental challenges to designing and implementing effective ML applications. Sensor/network failures that result in data stream interruptions is one such challenge. Unfortunately, the performance of many ML applications quickly degrades when faced with data incompleteness. Current techniques to handle data incompleteness are based upon data imputation ( i.e., they try to fill-in missing data). Unfortunately, these techniques may fail, especially when multiple sensors' data streams become concurrently unavailable (due to simultaneous sensor failures). With the aim of building robust IoT-coupled ML applications, this paper proposes SECOE, a unique, proactive approach for alleviating potentially simultaneous sensor failures. The fundamental idea behind SECOE is to create a carefully chosen ensemble of ML models in which each model is trained assuming a set of failed sensors (i.e., the training set omits corresponding values). SECOE includes a novel technique to minimize the number of models in the ensemble by harnessing the correlations among sensors. We demonstrate the efficacy of the SECOE approach through a series of experiments involving three distinct datasets. The experimental findings reveal that SECOE effectively preserves prediction accuracy in the presence of sensor failures.

To enable large-scale machine learning in bandwidth-hungry environments such as wireless networks, significant progress has been made recently in designing communication-efficient federated learning algorithms with the aid of communication compression. On the other end, privacy-preserving, especially at the client level, is another important desideratum that has not been addressed simultaneously in the presence of advanced communication compression techniques yet. In this paper, we propose a unified framework that enhances the communication efficiency of private federated learning with communication compression. Exploiting both general compression operators and local differential privacy, we first examine a simple algorithm that applies compression directly to differentially-private stochastic gradient descent, and identify its limitations. We then propose a unified framework SoteriaFL for private federated learning, which accommodates a general family of local gradient estimators including popular stochastic variance-reduced gradient methods and the state-of-the-art shifted compression scheme. We provide a comprehensive characterization of its performance trade-offs in terms of privacy, utility, and communication complexity, where SoteraFL is shown to achieve better communication complexity without sacrificing privacy nor utility than other private federated learning algorithms without communication compression.

Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts usually formulate text ranking as classification and rely on postprocessing to obtain a ranked list. In this paper, we propose RankT5 and study two T5-based ranking model structures, an encoder-decoder and an encoder-only one, so that they not only can directly output ranking scores for each query-document pair, but also can be fine-tuned with "pairwise" or "listwise" ranking losses to optimize ranking performances. Our experiments show that the proposed models with ranking losses can achieve substantial ranking performance gains on different public text ranking data sets. Moreover, when fine-tuned with listwise ranking losses, the ranking model appears to have better zero-shot ranking performance on out-of-domain data sets compared to the model fine-tuned with classification losses.

Creativity, i.e., the process of generating and developing fresh and original ideas or products that are useful or effective, is a valuable skill in a variety of domains. Creativity is called an essential 21st-century skill that should be taught in schools. The use of educational technology to promote creativity is an active study field, as evidenced by several studies linking creativity in the classroom to beneficial learning outcomes. Despite the burgeoning body of research on adaptive technology for education, mining creative thinking patterns from educational data remains a challenging task. In this paper, to address this challenge, we put the first step towards formalizing educational knowledge by constructing a domain-specific Knowledge Base to identify essential concepts, facts, and assumptions in identifying creative patterns. We then introduce a pipeline to contextualize the raw educational data, such as assessments and class activities. Finally, we present a rule-based approach to learning from the Knowledge Base, and facilitate mining creative thinking patterns from contextualized data and knowledge. We evaluate our approach with real-world datasets and highlight how the proposed pipeline can help instructors understand creative thinking patterns from students' activities and assessment tasks.

Sampling methods, as important inference and learning techniques, are typically designed for unconstrained domains. However, constraints are ubiquitous in machine learning problems, such as those on safety, fairness, robustness, and many other properties that must be satisfied to apply sampling results in real-life applications. Enforcing these constraints often leads to implicitly-defined manifolds, making efficient sampling with constraints very challenging. In this paper, we propose a new variational framework with a designed orthogonal-space gradient flow (O-Gradient) for sampling on a manifold $\mathcal{G}_0$ defined by general equality constraints. O-Gradient decomposes the gradient into two parts: one decreases the distance to $\mathcal{G}_0$ and the other decreases the KL divergence in the orthogonal space. While most existing manifold sampling methods require initialization on $\mathcal{G}_0$, O-Gradient does not require such prior knowledge. We prove that O-Gradient converges to the target constrained distribution with rate $\widetilde{O}(1/\text{the number of iterations})$ under mild conditions. Our proof relies on a new Stein characterization of conditional measure which could be of independent interest. We implement O-Gradient through both Langevin dynamics and Stein variational gradient descent and demonstrate its effectiveness in various experiments, including Bayesian deep neural networks.

Learning the underlying equation from data is a fundamental problem in many disciplines. Recent advances rely on Neural Networks (NNs) but do not provide theoretical guarantees in obtaining the exact equations owing to the non-convexity of NNs. In this paper, we propose Convex Neural Symbolic Learning (CoNSoLe) to seek convexity under mild conditions. The main idea is to decompose the recovering process into two steps and convexify each step. In the first step of searching for right symbols, we convexify the deep Q-learning. The key is to maintain double convexity for both the negative Q-function and the negative reward function in each iteration, leading to provable convexity of the negative optimal Q function to learn the true symbol connections. Conditioned on the exact searching result, we construct a Locally Convex equation Learner (LoCaL) neural network to convexify the estimation of symbol coefficients. With such a design, we quantify a large region with strict convexity in the loss surface of LoCaL for commonly used physical functions. Finally, we demonstrate the superior performance of the CoNSoLe framework over the state-of-the-art on a diverse set of datasets.

Neural Networks are known to be sensitive to initialisation. The methods that rely on neural networks for feature ranking are not robust since they can have variations in their ranking when the model is initialized and trained with different random seeds. In this work, we introduce a novel method based on parameter averaging to estimate accurate and robust feature importance in tabular data setting, referred as XTab. We first initialize and train multiple instances of a shallow network (referred as local masks) with "different random seeds" for a downstream task. We then obtain a global mask model by "averaging the parameters" of local masks. We show that although the parameter averaging might result in a global model with higher loss, it still leads to the discovery of the ground-truth feature importance more consistently than an individual model does. We conduct extensive experiments on a variety of synthetic and real-world data, demonstrating that the XTab can be used to obtain the global feature importance that is not sensitive to sub-optimal model initialisation.

Neural networks are known to produce poor uncertainty estimations, and a variety of approaches have been proposed to remedy this issue. This includes deep ensemble, a simple and effective method that achieves state-of-the-art results for uncertainty-aware learning tasks. In this work, we explore a combinatorial generalization of deep ensemble called deep combinatorial aggregation (DCA). DCA creates multiple instances of network components and aggregates their combinations to produce diversified model proposals and predictions. DCA components can be defined at different levels of granularity. And we discovered that coarse-grain DCAs can outperform deep ensemble for uncertainty-aware learning both in terms of predictive performance and uncertainty estimation. For fine-grain DCAs, we discover that an average parameterization approach named deep combinatorial weight averaging (DCWA) can improve the baseline training. It is on par with stochastic weight averaging (SWA) but does not require any custom training schedule or adaptation of BatchNorm layers. Furthermore, we propose a consistency enforcing loss that helps the training of DCWA and modelwise DCA. We experiment on in-domain, distributional shift, and out-of-distribution image classification tasks, and empirically confirm the effectiveness of DCWA and DCA approaches.

We consider the estimation of average and counterfactual treatment effects, under two settings: back-door adjustment and front-door adjustment. The goal in both cases is to recover the treatment effect without having an access to a hidden confounder. This objective is attained by first estimating the conditional mean of the desired outcome variable given relevant covariates (the "first stage" regression), and then taking the (conditional) expectation of this function as a "second stage" procedure. We propose to compute these conditional expectations directly using a regression function to the learned input features of the first stage, thus avoiding the need for sampling or density estimation. All functions and features (and in particular, the output features in the second stage) are neural networks learned adaptively from data, with the sole requirement that the final layer of the first stage should be linear. The proposed method is shown to converge to the true causal parameter, and outperforms the recent state-of-the-art methods on challenging causal benchmarks, including settings involving high-dimensional image data.

This paper develops a class of low-complexity device scheduling algorithms for over-the-air federated learning via the method of matching pursuit. The proposed scheme tracks closely the close-tooptimal performance achieved by difference-of-convex programming, and outperforms significantly the well-known benchmark algorithms based on convex relaxation. In the light of dramatically increasing numbers of mobile devices and data traffic in the Internet-of-Things era, the need for a paradigm-shift in wireless networks from traditional centralized cloud computing architectures to distributed ones is growing [1]-[5]. By performing data processing at the edge of networks, several shortcomings of cloud computing, such as long latency and network congestion, can be effectively addressed [6]-[8]. Notably, edge computing is an appealing technology to perform real-time tasks and make real-time decisions by exploiting the abundant computational resources of the edge servers [9]-[11]. H. Vincent Poor is with the Department of Electrical and Computer Engineering at the Princeton University; email: poor@princeton.edu. One way of overcoming these challenges is to integrate the edge-intelligent network within wireless networks and leverage the superposition property of wireless multiple-access channels [15]. Recently, a new paradigm of distributed machine learning, referred to as federated learning (FL) has been introduced, in which distributed devices jointly train a shared global machine learning model without sharing their raw data explicitly [16]-[18]. In essence, FL is a collaborative machine learning framework that enables distributed model training from decentralized data under coordination of a parameter server (PS) [17]. In principle FL is performed over a decentralized network as follows: 1) A PS first shares a global model with participating devices in the network. It then transmits its trained model parameters to the PS while keeping its private data locally within its own device. These steps are alternated until the global model parameters converge [16], [18], [19]. Further illustrations can be found through the comprehensive example of FL given in Appendix A. Compared to the extreme cases of centralized and individual learning, FL provides a tractable approach to handle a joint learning task over a distributed network. Nevertheless, this tractability comes with some costs which can be roughly categorized into three major forms: 1) The statistical inference problem in FL is more challenging. This follows from the fact that the local datasets in the decentralized setting are not independent and identically distributed (i.i.d.).