首页/论文/1908.06178

arXiv 1908.061782019-08-16cs.LGcs.AIstat.ML

Distributional Negative Sampling for Knowledge Base Completion

IBM Research AI（IBM研究院人工智能部门）

Sarthak Dash, Alfio Gliozzo

备注：: 8 pages

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities. In this paper, we argue that random sampling is not a good training strategy since it is highly likely to generate a huge number of nonsensical assertions during training, which does not provide relevant training signal to the system. Hence, it slows down the learning process and decreases accuracy. To address this issue, we propose an alternative approach called Distributional Negative Sampling that generates meaningful negative examples which are highly likely to be false. Our approach achieves a significant improvement in Mean Reciprocal Rank values amongst two different KBC algorithms in three standard academic benchmarks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

基于Wasserstein空间中最近邻的分布矩阵补全

Distributional Matrix Completion via Nearest Neighbors in the Wasserstein Space

Industrial Engineering and Operations Research, Columbia University（哥伦比亚大学工业工程与运筹学系）；Statistics and Data Science, Cornell Tech, Cornell University（康奈尔大学数据科学与统计学系）；Operations Research and Information Engineering, Cornell Tech, Cornell University（康奈尔大学运筹学与信息工程系）

本文将最优传输与最近邻方法结合，提出分布矩阵补全方法，在潜在因子模型下证明其Wasserstein恢复性质，并通过模拟和真实盈利预测数据验证其在分布估计、风险度量和异方差场景中的有效性。

2025-06-05cs.LGstat.MEstat.ML

低秩分布矩阵补全

Low-rank Distributional Matrix Completion

University of Texas at Dallas（德克萨斯大学达拉斯分校）；Texas A&M University（德克萨斯农工大学）

针对每个条目为概率分布的矩阵，提出基于核均值嵌入和Tucker秩的低秩结构，通过函数展开算子连接无限维与有限维，实现分布矩阵补全并给出非渐近误差界。

2026-06-02cs.LGmath.STstat.ML

半监督矩阵补全的泛化界限：带有分布侧信息的情况

Generalization Bounds for Semi-supervised Matrix Completion with Distributional Side Information

该研究提出了一种半监督矩阵补全方法，通过结合分布侧信息，推导出低秩矩阵补全的泛化界限，验证了在推荐系统中显式与隐式反馈交互的有效性。

2025-11-21cs.LGstat.ML

A Comparative Study of Distributional and Symbolic Paradigms for Relational Learning

KU Leuven（鲁汶大学）；EPFL（洛桑联邦理工学院）；NEC Labs（日本电气实验室）

Many real-world domains can be expressed as graphs and, more generally, as multi-relational knowledge graphs. Though reasoning and learning with knowledge graphs has traditionally been addressed by symbolic approaches, recent methods in (deep) representation learning has shown promising results for specialized tasks such as knowledge base completion. These approaches abandon the traditional symbolic paradigm by replacing symbols with vectors in Euclidean space. With few exceptions, symbolic and distributional approaches are explored in different communities and little is known about their resp…

2020-03-24cs.AIcs.LGstat.ML

基于混合几何张量分解的知识图谱补全

Knowledge Graph Completion with Mixed Geometry Tensor Factorization

HSE University（高等经济大学）；AIRI（人工智能研究所）

本文提出一种结合欧几里得与双曲几何的混合张量分解方法，通过引入双曲相互作用项修正Tucker分解模型，在显著减少参数的同时实现了SOTA的知识图谱链接预测精度。

2025-04-03cs.AIcs.IRcs.LG

TA-KAND: 两阶段注意力三重增强与U-KAN基于扩散的少样本知识图谱补全

TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion

Shanghai Jiao Tong University（上海交通大学）

TA-KAND通过两阶段注意力三重增强和U-KAN扩散模型，解决少样本知识图谱补全问题，实验表明其在两个公开数据集上表现优异。

2026-02-13cs.AIcs.LG

更多相关论文收起更多论文

Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations

Carnegie Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）；Roam Analytics

Knowledge graphs are a versatile framework to encode richly structured data relationships, but it can be challenging to combine these graphs with unstructured data. Methods for retrofitting pre-trained entity representations to the structure of a knowledge graph typically assume that entities are embedded in a connected space and that relations imply similarity. However, useful knowledge graphs often contain diverse entities and relations (with potentially disjoint underlying corpora) which do not accord with these assumptions. To overcome these limitations, we present Functional Retrofitting,…

2018-06-16cs.CLcs.LGstat.ML

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms

McGill University（麦吉尔大学）；Google Research（谷歌研究院）

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD($λ$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions, thus establishing their exponentially fast convergence to a stationary distribution. We demonstrate that the stationary distribution obtained by any algorithm whose target is an expected Bellman upda…

2020-03-27cs.AIcs.LGstat.ML

Canonical Tensor Decomposition for Knowledge Base Completion

Facebook AI Research（Facebook人工智能研究院）；Université Paris-Est（巴黎东大学）；Ecole des Ponts ParisTech（巴黎高等桥路学院）

The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) seems like a natural solution; however, current implementations of CP on standard Knowledge Base Completion benchmarks are lagging behind their competitors. In this work, we attempt to understand the limits of CP for knowledge base completion. First, we motivate and test a novel regularizer, based on tensor nuclear $p$-norms. Then, we present a reformulation of the problem that makes it invariant to arbitrary choices in…

2018-06-19cs.AIcs.LGcs.SI

探索分布式强化学习在噪声状态观测下的训练鲁棒性

Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations

University of Alberta（阿尔伯塔大学）；Harbin Engineering University（哈尔滨工程大学）；Huawei Kirin Solution（华为麒麟解决方案部）

本文研究分布式强化学习在噪声状态观测下的训练鲁棒性，通过理论分析梯度稳定性和实验验证，证明其优于基于期望的方法。

2023-06-21cs.LG

组级分布不确定性下的组分布鲁棒机器学习

Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty

Duke University（杜克大学）；KTH Royal Institute of Technology（皇家理工学院）

针对多源数据下最差组性能退化问题，提出基于Wasserstein距离的分布鲁棒优化框架，以应对组内分布不确定性，并开发梯度下降-上升算法求解，在真实数据上验证有效性。

2025-09-10cs.LG

Collaborative Training of Tensors for Compositional Distributional Semantics

University of Cambridge（剑桥大学）

Type-based compositional distributional semantic models present an interesting line of research into functional representations of linguistic meaning. One of the drawbacks of such models, however, is the lack of training data required to train each word-type combination. In this paper we address this by introducing training methods that share parameters between similar words. We show that these methods enable zero-shot learning for words that have no training data at all, as well as enabling construction of high-quality tensors from very few training examples per word.

2017-05-05cs.CLcs.LG

A Unified Wasserstein Distributional Robustness Framework for Adversarial Training

Monash University（莫纳什大学）；Adobe Research（Adobe研究院）；VinAI Research（VinAI研究院）

It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks, exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) method, by incorporating adversarial examples during training, represents a natural and effective approach to strengthen the robustness of a DNN-based classifier. However, most AT-based methods, notably PGD-AT and TRADES, typically seek a pointwise adversary that generates the worst-case adversarial example by independently perturbing each data sample, as a way to "probe" the vulnerability of the classifier. Arg…

2022-02-27cs.CVcs.LG