Federated learning (FL) typically relies on synchronous training, which is slow due to stragglers. While asynchronous training handles stragglers efficiently, it does not ensure privacy due to the incompatibility with the secure aggregation protocols. A buffered asynchronous training protocol known as FedBuff has been proposed recently which bridges the gap between synchronous and asynchronous training to mitigate stragglers and to also ensure privacy simultaneously. FedBuff allows the users to send their updates asynchronously while ensuring privacy by storing the updates in a trusted execution environment (TEE) enabled private buffer. TEEs, however, have limited memory which limits the buffer size. Motivated by this limitation, we develop a buffered asynchronous secure aggregation (BASecAgg) protocol that does not rely on TEEs. The conventional secure aggregation protocols cannot be applied in the buffered asynchronous setting since the buffer may have local models corresponding to different rounds and hence the masks that the users use to protect their models may not cancel out. BASecAgg addresses this challenge by carefully designing the masks such that they cancel out even if they correspond to different rounds. Our convergence analysis and experiments show that BASecAgg almost has the same convergence guarantees as FedBuff without relying on TEEs.

Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining highdimensional, low-precision, distributed representations of data. These representations can be combined with simple, neurally plausible algorithms to effect a variety of information processing tasks. HD computing has recently garnered significant interest from the computer hardware community as an energy-efficient, low-latency, and noise-robust tool for solving learning problems. In this review, we present a unified treatment of the theoretical foundations of HD computing with a focus on the suitability of representations for learning.

Institutions are increasingly relying on machine learning models Given the imbalanced nature of data in this domain, which makes to identify and alert on abnormal events, such as fraud, cyber attacks learning classifiers that efficiently discriminate among the minority and system failures. These alerts often need to be manually and majority class difficult, and the limited resources available investigated by specialists. Given the operational cost of manual inspections, for inspecting time-sensitive risky events, we are interested in understanding the suspicious events are selected by alerting systems with the relationship between the rate of detection from the carefully designed thresholds. In this paper, we consider an imbalanced minority class (i.e., the fraction of samples from the minority class binary classification problem, where events arrive sequentially selected for inspection) and the inspection budget. Specifically, we and only a limited number of suspicious events can be inspected. We focus on applications that involve real-time processing and decisionmaking model the event arrivals as a non-homogeneous Poisson process, and where an abnormal event can only be inspected at the time compare various suspicious event selection methods including those of arrival, and we investigate how different selection policies based based on static and adaptive thresholds. For each method, we analytically on classifier predictions operate in terms of the limited inspection characterize the tradeoff between the minority-class detection budget rather than the decision threshold.

Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and equivalent complex tasks) often pertain to various types of sub-tasks, requiring different kinds of reasoning. Certain types of reasoning have proven to be more difficult to learn in a monolingual context, and in the crosslingual context, similar observations may shed light on zero-shot transfer efficiency and few-shot sample selection. Hence, to investigate the effects of types of reasoning on transfer performance, we propose a category-annotated multilingual NLI dataset and discuss the challenges to scale monolingual annotations to multiple languages. We statistically observe interesting effects that the confluence of reasoning types and language similarities have on transfer performance.

Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction. Existing approaches explore the discrete nature of human intent before predicting continuous trajectories, to improve accuracy and support explainability. However, these approaches often assume the intent to remain fixed over the prediction horizon, which is problematic in practice, especially over longer horizons. To overcome this limitation, we introduce HYPER, a general and expressive hybrid prediction framework that models evolving human intent. By modeling traffic agents as a hybrid discrete-continuous system, our approach is capable of predicting discrete intent changes over time. We learn the probabilistic hybrid model via a maximum likelihood estimation problem and leverage neural proposal distributions to sample adaptively from the exponentially growing discrete space. The overall approach affords a better trade-off between accuracy and coverage. We train and validate our model on the Argoverse dataset, and demonstrate its effectiveness through comprehensive ablation studies and comparisons with state-of-the-art models.

A recent line of work [3, 5, 23, 29] has established intriguing connections between the generalization/compression properties of a deep neural network (DNN) model and the so-called layer weights' stable ranks. Intuitively, the latter are indicators of the effective number of parameters in the net. In this work, we address some natural questions regarding the space of DNNs conditioned on the layers' stable rank, where we study feed-forward dynamics, initialization, training and expressivity. To this end, we first propose a random DNN model with a new sampling scheme based on stable rank. Then, we show how feed-forward maps are affected by the constraint and how training evolves in the overparametrized regime (via Neural Tangent Kernels). Our results imply that stable ranks appear layerwise essentially as linear factors whose effect accumulates exponentially depthwise. Moreover, we provide empirical analysis suggesting that stable rank initialization alone can lead to convergence speed ups.

A program written with differentiable programming can be differentiated automatically. The differentiation results can then be used for gradient-based optimization (e.g., gradient descent) of the parameters in the program. Differentiable programming have been used in scientific computing, physics simulations, and other domains to help mitigate the burden of manual error-prone coding of derivative computations. Recent several years have witnessed a growing interest of differentiable programming in machine learning (ML) [11, 34] and Probabilistic Programming [30], to accommodate the needs of various customized ML operators, user-defined operations in the learning targets (e.g., the physical environment of reinforcement learning) and statistical sampling. The key technique in differentiable programming is automatic differentiation. For a program (P) that produces output (y) from some given values (X), automatic differentiation automatically computes the derivatives ( y/ x) (x X) without the need for users to write the differentiation code. The given program P is called the primal code, and x is called an active input variable. Existing approaches of automatic differentiation fall into two categories: (i) Symbolic differentiation, which uses expression manipulation in computer algebra systems, (ii) Algorithmic differentiation, which performs a non-standard interpretation of a given computer program by replacing the domain of the variables to incorporate derivative values and redefining the semantics of the operators to propagate derivatives per the chain rule of differential calculus (elaborated in Section 2). Symbolic differentiation has been commonly regarded inappropriate for differentiable programming, for several reasons: (i) It results in complex and cryptic expressions plagued with the problem of "expression swell" [5].

Contrastive learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negative samples) apart. As revealed in recent works, CL can benefit from hard negative samples (negative samples that are difficult to distinguish from the anchor). However, we observe minor improvement or even performance drop when we adopt existing hard negative mining techniques in Graph Contrastive Learning (GCL). We find that many hard negative samples similar to anchor point are false negative ones (samples from the same class as anchor point) in GCL, which is different from CL in computer vision and will lead to unsatisfactory performance of existing hard negative mining techniques in GCL. To eliminate this bias, we propose Debiased Graph Contrastive Learning (DGCL), a novel and effective method to estimate the probability whether each negative sample is true or not. With this probability, we devise two schemes (i.e., DGCL-weight and DGCL-mix) to boost the performance of GCL. Empirically, DGCL outperforms or matches previous unsupervised state-of-the-art results on several benchmarks and even exceeds the performance of supervised ones.

Network representation learning aims to generate an embedding for each node in a network, which facilitates downstream machine learning tasks such as node classification and link prediction. Current work mainly focuses on transductive network representation learning, i.e. generating fixed node embeddings, which is not suitable for real-world applications. Therefore, we propose a new inductive network representation learning method called MNCI by mining neighborhood and community influences in temporal networks. We propose an aggregator function that integrates neighborhood influence with community influence to generate node embeddings at any time. We conduct extensive experiments on several real-world datasets and compare MNCI with several state-of-the-art baseline methods on various tasks, including node classification and network visualization. The experimental results show that MNCI achieves better performance than baselines.

We characterize optimal oversight of algorithms in a world where an agent designs a complex prediction function but a principal is limited in the amount of information she can learn about the prediction function. We show that limiting agents to prediction functions that are simple enough to be fully transparent is inefficient as long as the bias induced by misalignment between principal's and agent's preferences is small relative to the uncertainty about the true state of the world. Algorithmic audits can improve welfare, but the gains depend on the design of the audit tools. Tools that focus on minimizing overall information loss, the focus of many post-hoc explainer tools, will generally be inefficient since they focus on explaining the average behavior of the prediction function rather than sources of mis-prediction, which matter for welfare-relevant outcomes. Targeted tools that focus on the source of incentive misalignment, e.g., excess false positives or racial disparities, can provide first-best solutions. We provide empirical support for our theoretical findings using an application in consumer lending.