Related papers: Training with Multi-Layer Embeddings for Model Red…
Recommender models are commonly used to suggest relevant items to a user for e-commerce and online advertisement-based applications. These models use massive embedding tables to store numerical representation of items' and users'…
Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year. Although the field benefits from the rapid progress, the divergence in training…
We introduce a novel continued pre-training method, MELT (MatEriaLs-aware continued pre-Training), specifically designed to efficiently adapt the pre-trained language models (PLMs) for materials science. Unlike previous adaptation…
The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set. Embedding based approaches make training and…
Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computational and statistical constraints for each downstream task…
Deep learning models are trained and deployed in multiple domains. Increasing usage of deep learning models alarms the usage of memory consumed while computation by deep learning models. Existing approaches for reducing memory consumption…
Manifold learning techniques have become increasingly valuable as data continues to grow in size. By discovering a lower-dimensional representation (embedding) of the structure of a dataset, manifold learning algorithms can substantially…
Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…
Embedding models are pivotal in industrial information retrieval systems like search and advertising. However, existing pretrained models often exhibit fixed architectures and embedding dimensionalities, posing significant challenges when…
Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and candidates. However, current methods either condense queries and candidates into a single vector, potentially limiting the…
Machine learning models and libraries can train datasets of different sizes and perform prediction and classification operations, but machine learning models and libraries cause slow and long training times on large datasets. This article…
The current deep learning model is of a single-grade, that is, it learns a deep neural network by solving a single nonconvex optimization problem. When the layer number of the neural network is large, it is computationally challenging to…
Deep Metric Learning (DML), a widely-used technique, involves learning a distance metric between pairs of samples. DML uses deep neural architectures to learn semantic embeddings of the input, where the distance between similar examples is…
Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain…
This paper studies the fast adaptive beamforming for the multiuser multiple-input single-output downlink. Existing deep learning-based approaches assume that training and testing channels follow the same distribution which causes task…
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work,…
In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as \textit{Model Transfer Reinforcement Learning (MTRL)}…
This paper proposes a method for learning joint embeddings of images and text using a two-branch neural network with multiple layers of linear projections followed by nonlinearities. The network is trained using a large margin objective…
Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a…
Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is…