Search

Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently. We demonstrate a training-time technique to produce superior embeddings via effective cross-category learning and theoretically explain its surprising effectiveness. The scheme, termed the multi-layer embeddings training (MLET), trains embeddings using factorization of the embedding layer, with an inner dimension higher than the target embedding dimension. For inference efficiency, MLET converts the trained two-layer embedding into a single-layer one thus keeping inference-time model size unchanged. Empirical superiority of MLET is puzzling as its search space is not larger than that of the single-layer embedding. The strong dependence of MLET on the inner dimension is even more surprising. We develop a theory that explains both of these behaviors by showing that MLET creates an adaptive update mechanism modulated by the singular vectors of embeddings. When tested on multiple state-of-the-art recommendation models for click-through rate (CTR) prediction tasks, MLET consistently produces better models, especially for rare items. At constant model quality, MLET allows embedding dimension, and model size, reduction by up to 16x, and 5.8x on average, across the models., Comment: This is the preprint of our paper accepted at ACML 2023

A primary design goal of the cell-free~(CF) massive MIMO architecture is to provide uniformly good coverage to all the user equipments~(UEs) connected to the network. However, it has been found that this requirement may not be satisfied in case the channels between the access points~(APs) and the UEs are mixed LoS/NLoS. In this paper, we try to address this issue via the use of appropriate power control in both the uplink and downlink of a CF massive MIMO system under mixed LoS/NLoS channels. We find that simplistic power control techniques, such as channel inversion-based power control perform sub-optimally as compared to max-min power control. As a consequence, we propose a particle swarm algorithm~(PSA) based power control algorithm to optimize the performance of the system under study. We then use numerical simulations to evaluate the performance of the proposed PSA-based solution and show that it results in a significant improvement in the fairness of the underlying system while incurring a lower computational complexity., Comment: 10 pages, 10 figures

Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to metrics like helpfulness, explainability, and visual-descriptiveness [15] leading to generated captions being misaligned with reader preferences. To enable the generation of high-quality figure captions, we introduce FigCaps-HF a new framework for figure-caption generation that can incorporate domain expert feedback in generating captions optimized for reader preferences. Our framework comprises of 1) an automatic method for evaluating quality of figure-caption pairs, 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences. We demonstrate the effectiveness of our simple learning framework by improving performance over standard fine-tuning across different types of models. In particular, when using BLIP as the base model, our RLHF framework achieves a mean gain of 35.7%, 16.9%, and 9% in ROUGE, BLEU, and Meteor, respectively. Finally, we release a large-scale benchmark dataset with human feedback on figure-caption pairs to enable further evaluation and development of RLHF techniques for this problem., Comment: 19 pages, 4 figures. Benchmark Documentation: https://figcapshf.github.io/

Wearable sensors such as Inertial Measurement Units (IMUs) are often used to assess the performance of human exercise. Common approaches use handcrafted features based on domain expertise or automatically extracted features using time series analysis. Multiple sensors are required to achieve high classification accuracy, which is not very practical. These sensors require calibration and synchronization and may lead to discomfort over longer time periods. Recent work utilizing computer vision techniques has shown similar performance using video, without the need for manual feature engineering, and avoiding some pitfalls such as sensor calibration and placement on the body. In this paper, we compare the performance of IMUs to a video-based approach for human exercise classification on two real-world datasets consisting of Military Press and Rowing exercises. We compare the performance using a single camera that captures video in the frontal view versus using 5 IMUs placed on different parts of the body. We observe that an approach based on a single camera can outperform a single IMU by 10 percentage points on average. Additionally, a minimum of 3 IMUs are required to outperform a single camera. We observe that working with the raw data using multivariate time series classifiers outperforms traditional approaches based on handcrafted or automatically extracted features. Finally, we show that an ensemble model combining the data from a single camera with a single IMU outperforms either data modality. Our work opens up new and more realistic avenues for this application, where a video captured using a readily available smartphone camera, combined with a single sensor, can be used for effective human exercise classification.

We develop a novel framework for single-scene video anomaly localization that allows for human-understandable reasons for the decisions the system makes. We first learn general representations of objects and their motions (using deep networks) and then use these representations to build a high-level, location-dependent model of any particular scene. This model can be used to detect anomalies in new videos of the same scene. Importantly, our approach is explainable - our high-level appearance and motion features can provide human-understandable reasons for why any part of a video is classified as normal or anomalous. We conduct experiments on standard video anomaly detection datasets (Street Scene, CUHK Avenue, ShanghaiTech and UCSD Ped1, Ped2) and show significant improvements over the previous state-of-the-art.

Subspace clustering algorithms are used for understanding the cluster structure that explains the dataset well. These methods are extensively used for data-exploration tasks in various areas of Natural Sciences. However, most of these methods fail to handle unwanted biases in datasets. For datasets where a data sample represents multiple attributes, naively applying any clustering approach can result in undesired output. To this end, we propose a novel framework for jointly removing unwanted attributes (biases) while learning to cluster data points in individual subspaces. Assuming we have information about the bias, we regularize the clustering method by adversarially learning to minimize the mutual information between the data and the unwanted attributes. Our experimental result on synthetic and real-world datasets demonstrate the effectiveness of our approach.

In April 2022, the Vistamilk SFI Research Centre organized the second edition of the "International Workshop on Spectroscopy and Chemometrics - Applications in Food and Agriculture". Within this event, a data challenge was organized among participants of the workshop. Such data competition aimed at developing a prediction model to discriminate dairy cows' diet based on milk spectral information collected in the mid-infrared region. In fact, the development of an accurate and reliable discriminant model for dairy cows' diet can provide important authentication tools for dairy processors to guarantee product origin for dairy food manufacturers from grass-fed animals. Different statistical and machine learning modelling approaches have been employed during the workshop, with different pre-processing steps involved and different degree of complexity. The present paper aims to describe the statistical methods adopted by participants to develop such classification model., Comment: 27 pages, 9 figures

Technological advancements have spurred the usage of machine learning based applications in sports science. Physiotherapists, sports coaches and athletes actively look to incorporate the latest technologies in order to further improve performance and avoid injuries. While wearable sensors are very popular, their use is hindered by constraints on battery power and sensor calibration, especially for use cases which require multiple sensors to be placed on the body. Hence, there is renewed interest in video-based data capture and analysis for sports science. In this paper, we present the application of classifying S\&C exercises using video. We focus on the popular Military Press exercise, where the execution is captured with a video-camera using a mobile device, such as a mobile phone, and the goal is to classify the execution into different types. Since video recordings need a lot of storage and computation, this use case requires data reduction, while preserving the classification accuracy and enabling fast prediction. To this end, we propose an approach named BodyMTS to turn video into time series by employing body pose tracking, followed by training and prediction using multivariate time series classifiers. We analyze the accuracy and robustness of BodyMTS and show that it is robust to different types of noise caused by either video quality or pose estimation factors. We compare BodyMTS to state-of-the-art deep learning methods which classify human activity directly from videos and show that BodyMTS achieves similar accuracy, but with reduced running time and model engineering effort. Finally, we discuss some of the practical aspects of employing BodyMTS in this application in terms of accuracy and robustness under reduced data quality and size. We show that BodyMTS achieves an average accuracy of 87\%, which is significantly higher than the accuracy of human domain experts.

Extensive research has been carried out in the past to estimate the bulk viscosity of dense monatomic fluids; however, little attention has been paid to estimate the same in the dilute gas regime. In this work, we perform precise Green-Kubo calculations in molecular dynamics simulations to estimate the bulk viscosity of dilute argon gas. The investigated temperature and pressure range is 300 to 750 K and 0.5 to 1.5 bar respectively. It is observed that the estimated bulk viscosity is $O(10^{-10})$ Pa s, which is several orders of magnitude smaller than that of other diatomic and polyatomic gases, but nonetheless, not an absolute zero as typically assumed. It implies that Stokes' hypothesis is true for dilute monatomic gases only in an approximate rather than absolute sense. The variation of bulk viscosity with pressures at constant temperatures has also been studied and is found to be of quadratic nature. The obtained bulk viscosity values are also reported in the reduced Lennard-Jones units to enable extension of the present results to other noble gases as well. It has also been observed that the bulk viscosity of Lennard-Jones monatomic gases becomes temperature independent at very low densities., Comment: 9 pages, 10 figures

We use dissipative particle dynamics (DPD) simulations to study the effect of shear on domain morphology and kinetics of microphase separating critical diblock copolymer (BCP) bulk melts. The melt is confined within two parallel solid walls at the top and bottom of the simulation box. The shear is induced by allowing the walls to move in a direction with a specific velocity. We explore the following cases: (i) walls are fixed, (ii) only the top wall moves, (iii) both walls move in the same direction, and (iv) both walls move in opposite directions. After the temperature quench, we monitor the effect of shear on evolution morphology, the scaling behavior of the system, and the characteristic length scale and growth. The characteristic length scale follows typical power-law behavior at early times and saturates at late times when both walls are fixed. The length scale changes significantly with shear caused by wall velocities. The usual lamellar morphology, which is not achieved for case 1 within the considered simulation time steps, is noticed much earlier for the nonzero wall velocity cases. Specifically, it is seen much before in case 4 than in the other cases. We find that the shear viscosity decreases (shear-thinning) with wall velocity (shear rate) for all the cases at a given coarsening time. Overall, we report the influence rule of shear rates on microphase separation kinetics of BCP melts. This study can provide a scheme to anticipate and design anisotropic microstructures under the application of externally controlled wall shear that may further guide in producing the various composite materials with superior mechanical and physical properties., Comment: 44 pages, 16 figures, article

A chemometric data analysis challenge has been arranged during the first edition of the "International Workshop on Spectroscopy and Chemometrics", organized by the Vistamilk SFI Research Centre and held online in April 2021. The aim of the competition was to build a calibration model in order to predict milk quality traits exploiting the information contained in mid-infrared spectra only. Three different traits have been provided, presenting heterogeneous degrees of prediction complexity thus possibly requiring trait-specific modelling choices. In this paper the different approaches adopted by the participants are outlined and the insights obtained from the analyses are critically discussed., Comment: 17 pages, 6 figures, 6 tables

Prediction of diabetes and its various complications has been studied in a number of settings, but a comprehensive overview of problem setting for diabetes prediction and care management has not been addressed in the literature. In this document we seek to remedy this omission in literature with an encompassing overview of diabetes complication prediction as well as situating this problem in the context of real world healthcare management. We illustrate various problems encountered in real world clinical scenarios via our own experience with building and deploying such models. In this manuscript we illustrate a Machine Learning (ML) framework for addressing the problem of predicting Type 2 Diabetes Mellitus (T2DM) together with a solution for risk stratification, intervention and management. These ML models align with how physicians think about disease management and mitigation, which comprises these four steps: Identify, Stratify, Engage, Measure.