Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

methodology-10

Entity Embeddings

3260 papers • 126 benchmarks • 313 datasets

Entity Embeddings is a technique for applying deep learning to tabular data. It involves representing the categorical data of an information systems entity with multiple dimensions.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in entity-embeddings-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find entity-embeddings-10 models and implementations

Datasets

DAWT

MovieGraphBenchmark

MovieGraphBenchmark

Subtasks

No subtasks available.

Most implemented papers

Entity Embeddings of Categorical Variables

Cheng Guo, Felix Berkhahn•Thu Apr 21 2016

It is demonstrated in this paper that entity embedding helps the neural network to generalize better when the data is sparse and statistics is unknown, and is especially useful for datasets with lots of high cardinality features, where other methods tend to overfit.

438

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Scalable Zero-shot Entity Linking with Dense Entity Retrieval

F. Petroni, Luke S. Zettlemoyer, Martin Josifoski, Ledell Wu, Sebastian Riedel•Sat Nov 09 2019

This paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off. We present a two-stage zero-shot linking algorithm, where each entity is defined only by a short textual description. The first stage does retrieval in a dense space defined by a bi-encoder that independently embeds the mention context and the entity descriptions. Each candidate is then re-ranked with a cross-encoder, that concatenates the mention and entity text. Experiments demonstrate that this approach is state of the art on recent zero-shot benchmarks (6 point absolute gains) and also on more established non-zero-shot evaluations (e.g. TACKBP-2010), despite its relative simplicity (e.g. no explicit entity embeddings or manually engineered mention tables). We also show that bi-encoder linking is very fast with nearest neighbor search (e.g. linking with 5.9 million candidates in 2 milliseconds), and that much of the accuracy gain from the more expensive cross-encoder can be transferred to the bi-encoder via knowledge distillation. Our code and models are available at https://github.com/facebookresearch/BLINK.

424 0

A deep learning system for predicting size and fit in fashion e-commerce

Roland Vollgraf, Urs M. Bergmann, Abdul-Saboor Sheikh, Romain Guigourès, Evgenii Koriagin, Yuen King Ho, Reza Shirvany•Mon Jul 22 2019

This work proposes a deep learning based content-collaborative methodology for personalized size and fit recommendation that can ingest arbitrary customer and article data and can model multiple individuals or intents behind a single account.

49 0

Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs

H. Dai, Le Song, Rakshit S. Trivedi, Yichen Wang•Mon May 15 2017

Know-Evolve is presented, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time that effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.

537 0

HyperTeNet: Hypergraph and Transformer-based Neural Network for Personalized List Continuation

S. Shevade, M. Vijaikumar, Deepesh V. Hada•Sun Oct 03 2021

This work proposes HyperTeNet - a self-attention hypergraph and Transformer-based neural network architecture for the personalized list continuation task that significantly outperforms the other state-of-the-art models on real-world datasets.

5 0

Rethinking Graph Convolutional Networks in Knowledge Graph Completion

Jieping Ye, Zhanqiu Zhang, Jie Wang, Feng Wu•Mon Feb 07 2022

It is suggested that existing GCNs are unnecessary for KGC, and novel GCN-based KGC models should count on more ablation studies to validate their effectiveness.

78 0

ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

Xiaoze Liu, Lu Chen, Yunjun Gao, Junyang Wu, Tianyi Li, Pengfei Wang•Thu May 19 2022

ClusterEA is presented, a general framework that is capable of scaling up EA models and enhancing their results by leveraging normalization methods on mini-batches with a high entity equivalent rate and contains three components to align entities between large-scale KGs, including stochastic training, ClusterSampler, and SparseFusion.

49 0

StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph

Hongzhu Li, Xiang Gao, Linhui Feng, Yafeng Deng, Yuhui Yin•Thu May 26 2022

The experimental results proves that StarGraph is efficient in parameters, and the improvement made on ogbl-wikikg2 demonstrates its great effectiveness of representation learning on large-scale knowledge graphs.

2 0

Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization

Jieming Zhu, Qijiong Liu, Jiaren Xiao, Lu Fan, Xiao-Ming Wu•Wed Aug 30 2023

This work devise a differentiable vector quantization framework for automatic category tree generation, namely CAGE, which enables the simultaneous learning and refinement of categorical code representations and entity embeddings in an end-to-end manner, starting from the randomly initialized states.

2 0

Named Entity Disambiguation for Noisy Text

Omer Levy, Ikuya Yamada, Yotam Eshel, N. Cohen, Kira Radinsky, Shaul Markovitch•Tue Jun 27 2017

A neural model is designed and trained with a novel method for sampling informative negative examples that significantly outperforms existing state-of-the-art methods on WikilinksNED while achieving comparable performance on a smaller newswire dataset.

96 0

Adding a benchmark result helps the community track progress.

Entity Embeddings | State-of-the-Art