English
Related papers

Related papers: Understanding and Improving Hyperbolic Deep Reinfo…

200 papers

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically…

Artificial Intelligence · Computer Science 2017-05-29 Maximilian Nickel , Douwe Kiela

Recent research in representation learning has shown that hierarchical data lends itself to low-dimensional and highly informative representations in hyperbolic space. However, even if hyperbolic embeddings have gathered attention in image…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Gabriel Moreira , Manuel Marques , João Paulo Costeira , Alexander Hauptmann

Incomplete Multi-View Clustering (IMVC) faces the challenge of learning discriminative representations from fragmentary observations while maintaining robustness against missing views. However, prevalent Euclidean-based methods suffer from…

Machine Learning · Computer Science 2026-04-21 Tianyi Chen , Haobo Wang , Kai Tang , Gengyu Lyu , Tianlei Hu , Gang Chen , Hong Ma , Meixiang Xiang

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

Robotics · Computer Science 2026-03-13 Jin Yang , Ping Wei , Yixin Chen , Nanning Zheng

The Reinforcement Learning (RL) building blocks, i.e. Q-functions and policy networks, usually take elements from the cartesian product of two domains as input. In particular, the input of the Q-function is both the state and the action,…

Machine Learning · Computer Science 2021-06-15 Shai Keynan , Elad Sarafian , Sarit Kraus

Reinforcement Learning (RL) remains a central optimisation framework in machine learning. Although RL agents can converge to optimal solutions, the definition of ``optimality'' depends on the environment's statistical properties. The…

Machine Learning · Computer Science 2026-01-14 Bert Verbruggen , Arne Vanhoyweghen , Vincent Ginis

Many high-dimensional and large-volume data sets of practical relevance have hierarchical structures induced by trees, graphs or time series. Such data sets are hard to process in Euclidean spaces and one often seeks low-dimensional…

Machine Learning · Computer Science 2021-09-16 Eli Chien , Chao Pan , Puoya Tabaghi , Olgica Milenkovic

Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space. However, natural language exhibits hierarchical structure from broad…

Information Retrieval · Computer Science 2026-02-10 Hiren Madhu , Ngoc Bui , Ali Maatouk , Leandros Tassiulas , Smita Krishnaswamy , Menglin Yang , Sukanta Ganguly , Kiran Srinivasan , Rex Ying

Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process. The discount factor values future rewards by an exponential scheme that leads to theoretical convergence guarantees of the Bellman…

Machine Learning · Statistics 2019-03-01 William Fedus , Carles Gelada , Yoshua Bengio , Marc G. Bellemare , Hugo Larochelle

Given the exponential growth of the volume of the ball w.r.t. its radius, the hyperbolic space is capable of embedding trees with arbitrarily small distortion and hence has received wide attention for representing hierarchical datasets.…

Machine Learning · Computer Science 2024-12-25 Gal Mishne , Zhengchao Wan , Yusu Wang , Sheng Yang

Hyperbolic embeddings are a class of representation learning methods that offer competitive performances when data can be abstracted as a tree-like graph. However, in practice, learning hyperbolic embeddings of hierarchical data is…

Machine Learning · Computer Science 2024-07-24 Zhangyu Wang , Lantian Xu , Zhifeng Kong , Weilong Wang , Xuyu Peng , Enyang Zheng

Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However,…

Artificial Intelligence · Computer Science 2026-03-09 Zihan Ye , Phil Chau , Raban Emunds , Jannis Blüml , Cedric Derstroff , Quentin Delfosse , Oleg Arenz , Kristian Kersting

In large-scale recommender systems, the user-item networks are generally scale-free or expand exponentially. The latent features (also known as embeddings) used to describe the user and item are determined by how well the embedding space…

Information Retrieval · Computer Science 2022-05-31 Menglin Yang , Min Zhou , Jiahong Liu , Defu Lian , Irwin King

Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embeddings of CL are arranged on a hypersphere where similarity…

Machine Learning · Computer Science 2025-02-25 Yifei Zhang , Hao Zhu , Menglin Yang , Jiahong Liu , Rex Ying , Irwin King , Piotr Koniusz

Embedding the data in hyperbolic spaces can preserve complex relationships in very few dimensions, thus enabling compact models and improving efficiency of machine learning (ML) algorithms. The underlying idea is that hyperbolic…

Machine Learning · Computer Science 2025-01-14 Vladimir Jaćimović

Graph representation learning in Euclidean space, despite its widespread adoption and proven utility in many domains, often struggles to effectively capture the inherent hierarchical and complex relational structures prevalent in real-world…

Machine Learning · Computer Science 2025-08-26 Menglin Yang , Min Zhou , Tong Zhang , Jiahong Liu , Zhihao Li , Lujia Pan , Hui Xiong , Irwin King

Hyperbolic geometry has emerged as an effective latent space for representing complex networks, owing to its ability to capture hierarchical organization and heterogeneous connectivity patterns using low-dimensional embeddings. As a result,…

Machine Learning · Computer Science 2026-05-01 Sofía Pérez Casulo , Marcelo Fiori , Bernardo Marenco , Federico Larroca

Hyperparameter sensitivity in Deep Reinforcement Learning (RL) is often accepted as unavoidable. However, it remains unclear whether it is intrinsic to the RL problem or exacerbated by specific training mechanisms. We investigate this…

Machine Learning · Computer Science 2026-02-06 Jan Malte Töpperwien , Aditya Mohan , Marius Lindauer

In this work, we devise a new, general-purpose reinforcement learning strategy for the optimal control of parametric dynamical systems. Such problems frequently arise in applied sciences and engineering and entail a significant complexity…

Machine Learning · Computer Science 2026-02-12 Nicolò Botteghi , Stefania Fresca , Mengwu Guo , Andrea Manzoni

Reinforcement learning (RL) is a popular technique that allows an agent to learn by trial and error while interacting with a dynamic environment. The traditional Reinforcement Learning (RL) approach has been successful in learning and…