Knowledge Distillation (KD) aims to transfer a more capable teacher model's knowledge to a lighter student model in order to improve the efficiency of the model, making it faster and more deployable. However, the student model's optimization process over the noisy pseudo labels (generated by the teacher model) is tricky and the amount of pseudo labels one can generate is limited due to Out of Memory (OOM) error. In this paper, we propose FlyKD (Knowledge Distillation on the Fly) which enables the generation of virtually unlimited number of pseudo labels, coupled with Curriculum Learning that greatly alleviates the optimization process over the noisy pseudo labels. Empirically, we observe that FlyKD outperforms vanilla KD and the renown Local Structure Preserving Graph Convolutional Network (LSPGCN). Lastly, with the success of Curriculum Learning, we shed light on a new research direction of improving optimization over noisy pseudo labels.

Familial Hypercholesterolemia (FH) is a genetic disorder characterized by elevated levels of Low-Density Lipoprotein (LDL) cholesterol or its associated genes. Early-stage and accurate categorization of FH is of significance allowing for timely interventions to mitigate the risk of life-threatening conditions. Conventional diagnosis approach, however, is complex, costly, and a challenging interpretation task even for experienced clinicians resulting in high underdiagnosis rates. Although there has been a recent surge of interest in using Machine Learning (ML) models for early FH detection, existing solutions only consider a binary classification task solely using classical ML models. Despite its significance, application of Deep Learning (DL) for FH detection is in its infancy, possibly, due to categorical nature of the underlying clinical data. The paper addresses this gap by introducing the FH-TabNet, which is a multi-stage tabular DL network for multi-class (Definite, Probable, Possible, and Unlikely) FH detection. The FH-TabNet initially involves applying a deep tabular data learning architecture (TabNet) for primary categorization into healthy (Possible/Unlikely) and patient (Probable/Definite) classes. Subsequently, independent TabNet classifiers are applied to each subgroup, enabling refined classification. The model's performance is evaluated through 5-fold cross-validation illustrating superior performance in categorizing FH patients, particularly in the challenging low-prevalence subcategories.

The increasing digitalization in industry and society leads to a growing abundance of data available to be processed and exploited. However, the high volume of data requires considerable computational resources for applying machine learning approaches. Prototype selection techniques have been applied to reduce the requirements of computational resources that are needed by these techniques. In this paper, we propose an approach for speeding up existing prototype selection techniques. It builds an abstract representation of the dataset, using the notion of spatial partition. The second step uses this abstract representation to prune the search space efficiently and select a set of candidate prototypes. After, some conventional prototype selection algorithms can be applied to the candidates selected by our approach. Our approach was integrated with five conventional prototype selection algorithms and tested on 14 widely recognized datasets used in classification tasks. The performance of the modified algorithms was compared to that of their original versions in terms of accuracy and reduction rate. The experimental results demonstrate that, overall, our proposed approach maintains accuracy while enhancing the reduction rate of the original prototype selection algorithms and simultaneously reducing their execution times.

Representation learning is a fundamental task in machine learning, aiming at uncovering structures from data to facilitate subsequent tasks. However, what is a good representation for planning and reasoning in a stochastic world remains an open problem. In this work, we posit that learning a distance function is essential to allow planning and reasoning in the representation space. We show that a geometric abstraction of the probabilistic world dynamics can be embedded into the representation space through asymmetric contrastive learning. Unlike previous approaches that focus on learning mutual similarity or compatibility measures, we instead learn an asymmetric similarity function that reflects the state reachability and allows multi-way probabilistic inference. Moreover, by conditioning on a common reference state (e.g. the observer's current state), the learned representation space allows us to discover the geometrically salient states that only a handful of paths can lead through. These states can naturally serve as subgoals to break down long-horizon planning tasks. We evaluate our method in gridworld environments with various layouts and demonstrate its effectiveness in discovering the subgoals.

Nonnegative Matrix Factorization (NMF) is a widely applied technique in the fields of machine learning and data mining. Graph Regularized Non-negative Matrix Factorization (GNMF) is an extension of NMF that incorporates graph regularization constraints. GNMF has demonstrated exceptional performance in clustering and dimensionality reduction, effectively discovering inherent low-dimensional structures embedded within high-dimensional spaces. However, the sensitivity of GNMF to noise limits its stability and robustness in practical applications. In order to enhance feature sparsity and mitigate the impact of noise while mining row sparsity patterns in the data for effective feature selection, we introduce the $\ell_{2,0}$-norm constraint as the sparsity constraints for GNMF. We propose an unsupervised feature learning framework based on GNMF\_$\ell_{20}$ and devise an algorithm based on PALM and its accelerated version to address this problem. Additionally, we establish the convergence of the proposed algorithms and validate the efficacy and superiority of our approach through experiments conducted on both simulated and real image data.

In federated learning (FL), the significant communication overhead due to the slow convergence speed of training the global model poses a great challenge. Specifically, a large number of communication rounds are required to achieve the convergence in FL. One potential solution is to employ the Newton-based optimization method for training, known for its quadratic convergence rate. However, the existing Newton-based FL training methods suffer from either memory inefficiency or high computational costs for local clients or the server. To address this issue, we propose an FL with approximated global Hessian (FAGH) method to accelerate FL training. FAGH leverages the first moment of the approximated global Hessian and the first moment of the global gradient to train the global model. By harnessing the approximated global Hessian curvature, FAGH accelerates the convergence of global model training, leading to the reduced number of communication rounds and thus the shortened training time. Experimental results verify FAGH's effectiveness in decreasing the number of communication rounds and the time required to achieve the pre-specified objectives of the global model performance in terms of training and test losses as well as test accuracy. Notably, FAGH outperforms several state-of-the-art FL training methods.

Spatially resolved transcriptomics represents a significant advancement in single-cell analysis by offering both gene expression data and their corresponding physical locations. However, this high degree of spatial resolution entails a drawback, as the resulting spatial transcriptomic data at the cellular level is notably plagued by a high incidence of missing values. Furthermore, most existing imputation methods either overlook the spatial information between spots or compromise the overall gene expression data distribution. To address these challenges, our primary focus is on effectively utilizing the spatial location information within spatial transcriptomic data to impute missing values, while preserving the overall data distribution. We introduce \textbf{stMCDI}, a novel conditional diffusion model for spatial transcriptomics data imputation, which employs a denoising network trained using randomly masked data portions as guidance, with the unmasked data serving as conditions. Additionally, it utilizes a GNN encoder to integrate the spatial position information, thereby enhancing model performance. The results obtained from spatial transcriptomics datasets elucidate the performance of our methods relative to existing approaches.

Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often employing lineplots as the visual representation of time series data. In this paper, we propose a novel approach that uses time-frequency spectrograms as the visual representation of time series data. We introduce the use of a vision transformer for multimodal learning, showcasing the advantages of our approach across diverse datasets from different domains. To evaluate its effectiveness, we compare our method against statistical baselines (EMA and ARIMA), a state-of-the-art deep learning-based approach (DeepAR), other visual representations of time series data (lineplot images), and an ablation study on using only the time series as input. Our experiments demonstrate the benefits of utilizing spectrograms as a visual representation for time series data, along with the advantages of employing a vision transformer for simultaneous learning in both the time and frequency domains.

Accurate 6D object pose estimation is essential for various robotic tasks. Uncertain pose estimates can lead to task failures; however, a certain degree of error in the pose estimates is often acceptable. Hence, by quantifying errors in the object pose estimate and acceptable errors for task success, robots can make informed decisions. This is a challenging problem as both the object pose uncertainty and acceptable error for the robotic task are often multi-modal and cannot be parameterized with commonly used uni-modal distributions. In this paper, we introduce a framework for evaluating robotic task success under object pose uncertainty, representing both the estimated error space of the object pose and the acceptable error space for task success using multi-modal non-parametric probability distributions. The proposed framework pre-computes the acceptable error space for task success using dynamic simulations and subsequently integrates the pre-computed acceptable error space over the estimated error space of the object pose to predict the likelihood of the task success. We evaluated the proposed framework on two mobile manipulation tasks. Our results show that by representing the estimated and the acceptable error space using multi-modal non-parametric distributions, we achieve higher task success rates and fewer failures.

Reservoir computing (RC) offers a neuromorphic framework that is particularly effective for processing spatiotemporal signals. Known for its temporal processing prowess, RC significantly lowers training costs compared to conventional recurrent neural networks. A key component in its hardware deployment is the ability to generate dynamic reservoir states. Our research introduces a novel dual-memory RC system, integrating a short-term memory via a WOx-based memristor, capable of achieving 16 distinct states encoded over 4 bits, and a long-term memory component using a TiOx-based memristor within the readout layer. We thoroughly examine both memristor types and leverage the RC system to process temporal data sets. The performance of the proposed RC system is validated through two benchmark tasks: isolated spoken digit recognition with incomplete inputs and Mackey-Glass time series prediction. The system delivered an impressive 98.84% accuracy in digit recognition and sustained a low normalized root mean square error (NRMSE) of 0.036 in the time series prediction task, underscoring its capability. This study illuminates the adeptness of memristor-based RC systems in managing intricate temporal challenges, laying the groundwork for further innovations in neuromorphic computing.