Search results

Due to intense competition and lack of real estate on the front page of large e-commerce platforms, sellers are sometimes motivated to garner non-genuine signals (clicks, add-to-carts, purchases) on their products, to make them appear more appealing to customers. This hurts customers’ trust on the platform, and also hurts genuine sellers who sell their items without looking to game the system. While it

The paradigm of pre-training followed by finetuning has become a standard procedure for NLP tasks, with a known problem of domain shift between the pre-training and downstream corpus. Previous works have tried to mitigate this problem with additional pre-training, either on the downstream corpus itself when it is large enough, or on a manually curated unlabeled corpus of a similar domain. In this paper,

Calibration means that forecasts and average realized frequencies are close. We develop the concept of forecast hedging, which consists of choosing the forecasts so as to guarantee that the expected track record can only improve. This yields all the calibration results by the same simple basic argument while differentiating between them by the forecast-hedging tools used: deterministic and fixed point based

Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds the future is both exciting and challenging, with individuals and organisations seeking to minimise risks and maximise utilities. The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges. This article provides a non-systematic review

In online applications with streaming data, awareness of how far the empirical training or test data has shifted away from its original data distribution can be crucial to the performance of the model. However, historical samples in the data stream may not be kept either due to space requirements or for regulatory reasons. To cope with such situations, we propose Continual Density Ratio Estimation (CDRE

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain data are accessible (e.g., no intent labels for the intent classification task). To this end, we first evaluate different language model based approaches that predict

The moiré effect provides an interpretation for the steering of antennas that form beams through internal spatial interferences. We make an explicit connection between such antennas and the moiré effect, and use it to model six planar antennas that steer by scaling, rotating, or translating operations. Three of the antennas illustrate how to use moiré patterns to generate antenna designs.

There is an increasing interest in continuous learning (CL), as data privacy is becoming a priority for real-world machine learning applications. Meanwhile, there is still a lack of academic NLP benchmarks that are applicable for realistic CL settings, which is a major challenge for the advancement of the field. In this paper we discuss some of the unrealistic data characteristics of public datasets, study

Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI (EAI) challenges only provide simulated indoor scenes with a limited number of layouts. This paper presents LUMINOUS, the first research framework that employs stateof-the-art indoor scene

Deep learning based forecasting methods have become the methods of choice in many applications of time series prediction or forecasting often outperforming other approaches. Consequently, over the last years, these methods are now ubiquitous in large-scale industrial forecasting applications and have consistently ranked among the best entries in forecasting competitions(e.g.,M4andM5). This practical success

Graph neural networks (GNN) have recently emerged as a vehicle for applying deep network architectures to graph and relational data. However, given the increasing size of industrial datasets, in many practical situations the message passing computations required for sharing information across GNN layers are no longer scalable. Although various sampling methods have been introduced to approximate full-graph

We devise a coreset selection method based on the idea of gradient matching: the gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. We evaluate the method in the context of continual learning, where it can be used to curate a rehearsal memory. Our method performs strong competitors such as reservoir sampling across a range of memory sizes

Batch-mode active learning iteratively selects a batch of unlabeled samples for labelling to maximize model performance and reduce total runtime. To select the most informative and diverse batch, existing methods usually calculate the correlation between samples within a batch, leading to combinatorial optimization problems which are inefficient, complex, and limited to linear models for approximated solutions

We consider the task of 3D pose estimation and tracking of multiple people seen in an arbitrary number of camera feeds. We propose TesseTrack1, a novel top-down approach that simultaneously reasons about multiple individuals’ 3D body joint reconstructions and associations in space and time in a single end-to-end learnable framework. At the core of our approach is a novel spatio-temporal formulation that

For supervised learning with tabular data, decision tree ensembles produced via boosting techniques generally dominate real-world applications involving iid training/test sets. However for graph data where the iid assumption is violated due to structured relations between samples, it remains unclear how to best incorporate this structure within existing boosting pipelines. To this end, we propose a generalized

Probabilistic inference of Neural Network parameters is challenging due to the highly multi-modal likelihood functions. Most importantly, the permutation invariance of the neurons of the hidden layers renders the likelihood function unidentifiable with a factorial number of equivalent (symmetric) modes, independent of the data. We show that variational Bayesian methods that approximate the (multi-modal)

Natural language understanding (NLU) is one of the most critical components in goal-oriented dialog systems and enables innovative Big Data applications such as intelligent voice assistants (IVA) and chatbots. While recent advances in deep learning-based NLU models have achieved significant improvements in terms of accuracy, most existing works are monolingual or bilingual. In this work, we propose and

Training neural machine translation (NMT) models in federated learning (FL) settings could be inefficient both computationally and communication-wise, due to the large size of translation engines as well as the multiple rounds of updates required to train clients and a central server. In this paper, we explore how to efficiently build NMT models in an FL setup by proposing a novel solution. In order to

Motivated by modern applications, such as online advertisement and recommender systems, we study the top-k eXtreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select k arms and observe all or some of the rewards for the chosen arms. We first propose an algorithm for the non-eXtreme realizable setting, utilizing the Inverse Gap Weighting strategy

The event is over, but Amazon Science interviewed each of the six speakers within the Science of Machine Learning track. See what they had to say.