One-shot Learning for Temporal Knowledge Graphs
- URL: http://arxiv.org/abs/2010.12144v1
- Date: Fri, 23 Oct 2020 03:24:44 GMT
- Title: One-shot Learning for Temporal Knowledge Graphs
- Authors: Mehrnoosh Mirtaheri, Mohammad Rostami, Xiang Ren, Fred Morstatter,
Aram Galstyan
- Abstract summary: We propose a one-shot learning framework for link prediction in temporal knowledge graphs.
Our proposed method employs a self-attention mechanism to effectively encode temporal interactions between entities.
Our experiments show that the proposed algorithm outperforms the state of the art baselines for two well-studied benchmarks.
- Score: 49.41854171118697
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Most real-world knowledge graphs are characterized by a long-tail relation
frequency distribution where a significant fraction of relations occurs only a
handful of times. This observation has given rise to recent interest in
low-shot learning methods that are able to generalize from only a few examples.
The existing approaches, however, are tailored to static knowledge graphs and
not easily generalized to temporal settings, where data scarcity poses even
bigger problems, e.g., due to occurrence of new, previously unseen relations.
We address this shortcoming by proposing a one-shot learning framework for link
prediction in temporal knowledge graphs. Our proposed method employs a
self-attention mechanism to effectively encode temporal interactions between
entities, and a network to compute a similarity score between a given query and
a (one-shot) example. Our experiments show that the proposed algorithm
outperforms the state of the art baselines for two well-studied benchmarks
while achieving significantly better performance for sparse relations.
Related papers
- Temporal Smoothness Regularisers for Neural Link Predictors [8.975480841443272]
We show that a simple method like TNTComplEx can produce significantly more accurate results than state-of-the-art methods.
We also evaluate the impact of a wide range of temporal smoothing regularisers on two state-of-the-art temporal link prediction models.
arXiv Detail & Related papers (2023-09-16T16:52:49Z) - On the Importance of Spatial Relations for Few-shot Action Recognition [109.2312001355221]
In this paper, we investigate the importance of spatial relations and propose a more accurate few-shot action recognition method.
A novel Spatial Alignment Cross Transformer (SA-CT) learns to re-adjust the spatial relations and incorporates the temporal information.
Experiments reveal that, even without using any temporal information, the performance of SA-CT is comparable to temporal based methods on 3/4 benchmarks.
arXiv Detail & Related papers (2023-08-14T12:58:02Z) - From Temporal to Contemporaneous Iterative Causal Discovery in the
Presence of Latent Confounders [6.365889364810238]
We present a constraint-based algorithm for learning causal structures from observational time-series data.
We assume a discrete-time, stationary structural vector autoregressive process, with both temporal and contemporaneous causal relations.
The presented algorithm gradually refines a causal graph by learning long-term temporal relations before short-term ones, where contemporaneous relations are learned last.
arXiv Detail & Related papers (2023-06-01T12:46:06Z) - Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic
Representations [1.8262547855491458]
We introduce Time-LowFER, a family of parameter-efficient and time-aware extensions of the low-rank tensor factorization model LowFER.
Noting several limitations in current approaches to represent time, we propose a cycle-aware time-encoding scheme for time features.
We implement our methods in a unified temporal knowledge graph embedding framework, focusing on time-sensitive data processing.
arXiv Detail & Related papers (2022-04-10T22:24:11Z) - A Low Rank Promoting Prior for Unsupervised Contrastive Learning [108.91406719395417]
We construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning.
Our hypothesis explicitly requires that all the samples belonging to the same instance class lie on the same subspace with small dimension.
Empirical evidences show that the proposed algorithm clearly surpasses the state-of-the-art approaches on multiple benchmarks.
arXiv Detail & Related papers (2021-08-05T15:58:25Z) - Model-Agnostic Graph Regularization for Few-Shot Learning [60.64531995451357]
We present a comprehensive study on graph embedded few-shot learning.
We introduce a graph regularization approach that allows a deeper understanding of the impact of incorporating graph information between labels.
Our approach improves the performance of strong base learners by up to 2% on Mini-ImageNet and 6.7% on ImageNet-FS.
arXiv Detail & Related papers (2021-02-14T05:28:13Z) - Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs [49.6661602019124]
We study a spectrum of models derived by generalizing the current state of the art for few-shot link prediction.
We find that a simple zero-shot baseline - which ignores any relation-specific information - achieves surprisingly strong performance.
Experiments on carefully crafted synthetic datasets show that having only a few examples of a relation fundamentally limits models from using fine-grained structural information.
arXiv Detail & Related papers (2021-02-05T21:04:31Z) - Addressing Class Imbalance in Scene Graph Parsing by Learning to
Contrast and Score [65.18522219013786]
Scene graph parsing aims to detect objects in an image scene and recognize their relations.
Recent approaches have achieved high average scores on some popular benchmarks, but fail in detecting rare relations.
This paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem.
arXiv Detail & Related papers (2020-09-28T13:57:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.