Related papers: Efficient Retrieval Scaling with Hierarchical Inde…

Large-scale Hierarchical Classification (HC) involves datasets consisting of thousands of classes and millions of training instances with high-dimensional features posing several big data challenges. Feature selection that aims to select…

Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based…

Machine learning is the dominant approach to artificial intelligence, through which computers learn from data and experience. In the framework of supervised learning, a necessity for a computer to learn from data accurately and efficiently…

Sequence models in reinforcement learning require task knowledge to estimate the task policy. This paper presents a hierarchical algorithm for learning a sequence model from demonstrations. The high-level mechanism guides the low-level…

Searching, browsing, and recommendations are common ways in which the "choice overload" faced by users in the online marketplace can be mitigated. In this paper we propose the use of hierarchical item categories, obtained from implicit…

Candidate retrieval is a fundamental issue in recommendation system. Given user's recommendation request, relevant candidates need to be retrieved in realtime for subsequent ranking operations. Considering that the retrieval operation is…

Multi-scale inference is commonly used to improve the results of semantic segmentation. Multiple images scales are passed through a network and then the results are combined with averaging or max pooling. In this work, we present an…

To achieve scenario intelligence, humans must transfer knowledge to robots by developing goal-oriented algorithms, which are sometimes insensitive to dynamically changing environments. While deep reinforcement learning achieves significant…

We address the task of ranking objects (such as people, blogs, or verticals) that, unlike documents, do not have direct term-based representations. To be able to match them against keyword queries, evidence needs to be amassed from…

Contextual bandit learning is an increasingly popular approach to optimizing recommender systems via user feedback, but can be slow to converge in practice due to the need for exploring a large feature space. In this paper, we propose a…

Human data labeling is an important and expensive task at the heart of supervised learning systems. Hierarchies help humans understand and organize concepts. We ask whether and how concept hierarchies can inform the design of annotation…

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an…

Online learning is the cornerstone of applications like recommendation and advertising systems, where models continuously adapt to shifting data distributions. Model training for such systems is remarkably expensive, a cost that multiplies…

With the explosive growth of users and items, Recommender Systems are facing unprecedented challenges in terms of retrieval efficiency and storage overhead. Learning to Hash techniques have emerged as a promising solution to these issues by…

While scaling laws promise significant performance gains for recommender systems, efficiently deploying hyperscale models remains a major unsolved challenge. In contrast to fields where FMs are already widely adopted such as natural…

Indexes are models: a B-Tree-Index can be seen as a model to map a key to the position of a record within a sorted array, a Hash-Index as a model to map a key to a position of a record within an unsorted array, and a BitMap-Index as a model…

Dense embedding-based retrieval is widely used for semantic search and ranking. However, conventional two-stage approaches, involving contrastive embedding learning followed by approximate nearest neighbor search (ANNS), can suffer from…

We are interested in building collaborative filtering models for recommendation systems where users interact with slates instead of individual items. These slates can be hierarchical in nature. The central idea of our approach is to learn…

Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding…

Recently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains…