HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems

@article{VinhTran2020HyperMLAB,
  title={HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems},
  author={Lucas Vinh Tran and Yi Tay and Shuai Zhang and G. Cong and Xiaoli Li},
  journal={Proceedings of the 13th International Conference on Web Search and Data Mining},
  year={2020}
}
  • Lucas Vinh Tran, Yi Tay, +2 authors Xiaoli Li
  • Published 5 September 2018
  • Computer Science, Mathematics
  • Proceedings of the 13th International Conference on Web Search and Data Mining
This paper investigates the notion of learning user and item representations in non-Euclidean space. Specifically, we study the connection between metric learning in hyperbolic space and collaborative filtering by exploring Mobius gyrovector spaces where the formalism of the spaces could be utilized to generalize the most common Euclidean vector operations. Overall, this work aims to bridge the gap between Euclidean and hyperbolic geometry in recommender systems through metric learning approach… Expand
Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systems
TLDR
This paper answers the questions that which type of models and datasets are more suited for hyperbolic space, as well as which latent size to choose, and proposes a new metric learning based recommendation method called SCML and itshyperbolic version HSCML. Expand
Hyperbolic Neural Collaborative Recommender
TLDR
A deep hyperbolic representation learning method that exploits mutual semantic relations among users/items for collaborative filtering tasks and shows that HNCR outperforms its Euclidean counterpart and state-of-the-art baselines. Expand
HGCF: Hyperbolic Graph Convolution Networks for Collaborative Filtering
TLDR
This paper demonstrates that the model can be effectively learned with a margin ranking loss, and shows that hyperbolic space has desirable properties under the rank margin setting, and conducts extensive empirical analysis on three public benchmarks and compares against a large set of baselines. Expand
Learning User Representations with Hypercuboids for Recommender Systems
TLDR
A new user interest representation model for personalized recommendation that explicitly models user interests as a hypercuboid instead of a point in the space to alleviate the potential geometric inflexibility of existing collaborative filtering approaches. Expand
Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
TLDR
A simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem using only a single hidden layer achieves a competitive performance with respect to the current state-of-the-art. Expand
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
TLDR
A new method, the use of Finsler metrics integrated in a Riemannian optimization scheme, that better adapts to dissimilar structures in the graph is introduced, and a tool to analyze the embeddings and infer structural properties of the data sets is developed. Expand
Knowledge-Enhanced Top-K Recommendation in Poincaré Ball
TLDR
This work proposes a recommendation model in the hyperbolic space, which facilitates the learning of the hierarchical structure of knowledge graphs, and proposes an adaptive and finegrained regularization mechanism to adaptively regularize items and their neighboring representations. Expand
HSR: Hyperbolic Social Recommender
TLDR
It is shown that the proposed Hyperbolic Social Recommender outperforms its Euclidean counterpart and state-of-the-art social recommenders in click-through rate prediction and top-K recommendation, demonstrating the effectiveness of social recommendation in the hyperbolic space. Expand
HyperSoRec: Exploiting Hyperbolic User and Item Representations with Multiple Aspects for Social-aware Recommendation
Social recommendation has achieved great success in many domains including e-commerce and location-based social networks. Existing methods usually explore the user-item interactions or user-userExpand
HME: A Hyperbolic Metric Embedding Approach for Next-POI Recommendation
TLDR
A novel hyperbolic metric embedding (HME) model is proposed, which projects the check-in data into aHyperbolic space, which can effectively capture the underlying hierarchical structures, which are implied by the power-law distributions of user movements. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 51 REFERENCES
Signed Distance-based Deep Memory Recommender
TLDR
This paper designs and proposes a deep learning framework called Signed Distance-based Deep Memory Recommender, which captures non-linear relationships between users and items explicitly and implicitly, and work well in both general recommendation task and shopping basket-based recommendation task. Expand
Scalable Hyperbolic Recommender Systems
TLDR
The viability of hyperbolic geometry for recommender systems is demonstrated, showing that they significantly outperform Euclidean models on datasets with the properties of complex networks. Expand
Collaborative Metric Learning
TLDR
The proposed algorithm outperforms state-of-the-art collaborative filtering algorithms on a wide range of recommendation tasks and uncovers the underlying spectrum of users' fine-grained preferences. Expand
Lorentzian Distance Learning for Hyperbolic Representations
TLDR
An approach to learn representations based on the Lorentzian distance in hyperbolic geometry, which makes it appropriate to represent hierarchies where parent nodes minimize the distances to their descendants and have smaller Euclidean norm than their children. Expand
Hyperbolic Neural Networks
TLDR
This work combines the formalism of Mobius gyrovector spaces with the Riemannian geometry of the Poincare model of hyperbolic spaces to derivehyperbolic versions of important deep learning tools: multinomial logistic regression, feed-forward and recurrent neural networks such as gated recurrent units. Expand
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
TLDR
This work presents a novel method to embed directed acyclic graphs through hierarchical relations as partial orders defined using a family of nested geodesically convex cones and proves that these entailment cones admit an optimal shape with a closed form expression both in the Euclidean and hyperbolic spaces. Expand
Neural Embeddings of Graphs in Hyperbolic Space
TLDR
A new concept that exploits recent insights and proposes learning neural embeddings of graphs in hyperbolic space is presented and experimental evidence that embedding graphs in their natural geometry significantly improves performance on downstream tasks for several real-world public datasets is provided. Expand
Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking
TLDR
Qualitative studies demonstrate evidence that the proposed model is able to infer and encode explicit sentiment, temporal and attribute information despite being only trained on implicit feedback, ascertains the ability of LRML to uncover hidden relational structure within implicit datasets. Expand
Poincaré Embeddings for Learning Hierarchical Representations
TLDR
This work introduces a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincare ball -- and introduces an efficient algorithm to learn the embeddings based on Riemannian optimization. Expand
Large-Margin Classification in Hyperbolic Space
TLDR
Hyperbolic SVM, a hyperbolic formulation of support vector machine classifiers, is introduced and its theoretical connection to the Euclidean counterpart is described, allowing end-to-end analyses based on the inherenthyperbolic geometry of the data without resorting to ill-fitting tools developed for Euclidan space. Expand
...
1
2
3
4
5
...