While several self-supervised approaches for learning discrete speech representation have been proposed, it is unclear how these seemingly similar approaches relate to each other. In this paper, we consider a generative model with discrete latent variables that learns a discrete representation for speech. The objective of learning the generative model is formulated as information-theoretic co-training. Besides the wide generality, the objective can be optimized with several approaches, subsuming HuBERT-like training and vector quantization for learning discrete representation. Empirically, we find that the proposed approach learns discrete representation that is highly correlated with phonetic units, more correlated than HuBERT-like training and vector quantization.

The traditional methods for detecting autism spectrum disorder (ASD) are expensive, subjective, and time-consuming, often taking years for a diagnosis, with many children growing well into adolescence and even adulthood before finally confirming the disorder. Recently, graph-based learning techniques have demonstrated impressive results on resting-state functional magnetic resonance imaging (rs-fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE). We introduce IMAGIN, a multI-granular, Multi-Atlas spatio-temporal attention Graph Isomorphism Network, which we use to learn graph representations of dynamic functional brain connectivity (chronnectome), as opposed to static connectivity (connectome). The experimental results demonstrate that IMAGIN achieves a 5-fold cross-validation accuracy of 79.25%, which surpasses the current state-of-the-art by 1.5%. In addition, analysis of the spatial and temporal attention scores provides further validation for the neural basis of autism.

We present fast classification techniques for sparse generalized linear and additive models. These techniques can handle thousands of features and thousands of observations in minutes, even in the presence of many highly correlated features. For fast sparse logistic regression, our computational speed-up over other best-subset search techniques owes to linear and quadratic surrogate cuts for the logistic loss that allow us to efficiently screen features for elimination, as well as use of a priority queue that favors a more uniform exploration of features. As an alternative to the logistic loss, we propose the exponential loss, which permits an analytical solution to the line search at each iteration. Our algorithms are generally 2 to 5 times faster than previous approaches. They produce interpretable models that have accuracy comparable to black box models on challenging datasets.

Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server. While it is theoretically well-known that FL yields an optimal model -- centrally trained model assuming availability of all the edge device data at the central server -- under mild condition, in practice, it often requires massive amount of iterations until convergence, especially under presence of statistical/computational heterogeneity. This paper utilizes cyclic learning rate at the server side to reduce the number of training iterations with increased performance without any additional computational costs for both the server and the edge devices. Numerical results validate that, simply plugging-in the proposed cyclic aggregation to the existing FL algorithms effectively reduces the number of training iterations with improved performance.

With accurate and timely traffic forecasting, the impacted traffic conditions can be predicted in advance to guide agencies and residents to respond to changes in traffic patterns appropriately. However, existing works on traffic forecasting mainly relied on historical traffic patterns confining to short-term prediction, under 1 hour, for instance. To better manage future roadway capacity and accommodate social and human impacts, it is crucial to propose a flexible and comprehensive framework to predict physical-aware long-term traffic conditions for public users and transportation agencies. In this paper, the gap of robust long-term traffic forecasting was bridged by taking social media features into consideration. A correlation study and a linear regression model were first implemented to evaluate the significance of the correlation between two time-series data, traffic intensity and Twitter data intensity. Two time-series data were then fed into our proposed social-aware framework, Traffic-Twitter Transformer, which integrated Nature Language representations into time-series records for long-term traffic prediction. Experimental results in the Great Seattle Area showed that our proposed model outperformed baseline models in all evaluation matrices. This NLP-joined social-aware framework can become a valuable implement of network-wide traffic prediction and management for traffic agencies.

In this paper, we study the connection between the companies in the Swedish capital market. We consider 28 companies included in the determination of the market index OMX30. The network structure of the market is constructed using different methods to determine the distance between the companies. We use hierarchical clustering methods to find the relation among the companies in each window. Next, we obtain one-dimensional time series of the distances between the clustering trees that reflect the changes in the relationship between the companies in the market over time. The method of statistical process control, namely the Shewhart control chart, is applied to those time series to detect abnormal changes in the financial market.

We consider the pool-based active learning problem, where only a subset of the training data is labeled, and the goal is to query a batch of unlabeled samples to be labeled so as to maximally improve model performance. We formulate the problem using constrained learning, where a set of constraints bounds the performance of the model on labeled samples. Considering a primal-dual approach, we optimize the primal variables, corresponding to the model parameters, as well as the dual variables, corresponding to the constraints. As each dual variable indicates how significantly the perturbation of the respective constraint affects the optimal value of the objective function, we use it as a proxy of the informativeness of the corresponding training sample. Our approach, which we refer to as Active Learning via Lagrangian dualitY, or ALLY, leverages this fact to select a diverse set of unlabeled samples with the highest estimated dual variables as our query set. We demonstrate the benefits of our approach in a variety of classification and regression tasks and discuss its limitations depending on the capacity of the model used and the degree of redundancy in the dataset. We also examine the impact of the distribution shift induced by active sampling and show that ALLY can be used in a generative mode to create novel, maximally-informative samples.

Unsupervised representation learning for speech audios attained impressive performances for speech recognition tasks, particularly when annotated speech is limited. However, the unsupervised paradigm needs to be carefully designed and little is known about what properties these representations acquire. There is no guarantee that the model learns meaningful representations for valuable information for recognition. Moreover, the adaptation ability of the learned representations to other domains still needs to be estimated. In this work, we explore learning domain-invariant representations via a direct mapping of speech representations to their corresponding high-level linguistic informations. Results prove that the learned latents not only capture the articulatory feature of each phoneme but also enhance the adaptation ability, outperforming the baseline largely on accented benchmarks.

In distributed learning systems, robustness issues may arise from two sources. On one hand, due to distributional shifts between training data and test data, the trained model could exhibit poor out-of-sample performance. On the other hand, a portion of working nodes might be subject to byzantine attacks which could invalidate the learning result. Existing works mostly deal with these two issues separately. In this paper, we propose a new algorithm that equips distributed learning with robustness measures against both distributional shifts and byzantine attacks. Our algorithm is built on recent advances in distributionally robust optimization as well as norm-based screening (NBS), a robust aggregation scheme against byzantine attacks. We provide convergence proofs in three cases of the learning model being nonconvex, convex, and strongly convex for the proposed algorithm, shedding light on its convergence behaviors and endurability against byzantine attacks. In particular, we deduce that any algorithm employing NBS (including ours) cannot converge when the percentage of byzantine nodes is 1/3 or higher, instead of 1/2, which is the common belief in current literature. The experimental results demonstrate the effectiveness of our algorithm against both robustness issues. To the best of our knowledge, this is the first work to address distributional shifts and byzantine attacks simultaneously.

While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial edge devices. While existing works on FL mitigate such compromised devices by only aggregating a subset of the local models at the server side, they still cannot successfully ignore the outliers due to imprecise scoring rule. In this paper, we propose an effective Byzantine-robust FL framework, namely dummy contrastive aggregation, by defining a novel scoring function that sensitively discriminates whether the model has been poisoned or not. Key idea is to extract essential information from every local models along with the previous global model to define a distance measure in a manner similar to triplet loss. Numerical results validate the advantage of the proposed approach by showing improved performance as compared to the state-of-the-art Byzantine-resilient aggregation methods, e.g., Krum, Trimmed-mean, and Fang.