Learning over dynamic graphs poses major challenges, including capturing the evolving relationship in the graphs. Inspired by the advantages of hyperbolic embedding in static graphs, the hyperbolic space is expected to capture complex interactions in dynamic graphs. However, due to the distortion errors in the standard tangent space mappings, hyperbolic methods become more sensitive to noise and reduce the learning capacity. To address the distortion in tangent space, we proposed HMPTGN, a temporal graph network that operates directly on the hyperbolic manifold. In this journal paper, we introduce the HMPTGN+ architecture, an extension of the original HMPTGN with major updates to learn better representations of dynamic graphs based on the hyperbolic embedding. Our framework incorporates a high-order graph neural network for extracting spatial dependencies, a dilated causal attention mechanism for modeling temporal patterns while preserving causality, and a curvature-awareness mechanism to capture dynamic structures. Extensive experiments demonstrate the effectiveness of our proposed HMPTGN+ framework over state-of-the-art baselines in both temporal link prediction and temporal new link prediction tasks.

Many real-world graphs exhibit diverse and complex topological structures that are not well captured by geometric manifolds with uniform global curvature, such as hyperbolic or spherical spaces. Recently, there has been growing interest in embedding graphs into pseudo-Riemannian manifolds, which generalize both hyperbolic and spherical geometries. However, existing approaches face three significant limitations, including the ineffective pseudo-Riemannain framework, the shallow architectures, and the absence of clear guideline for selecting suitable pseudo-Riemannian manifolds. To address these issues, we introduce a novel diffeomorphic framework for graph embedding that aligns with the nature of pseudo-Riemannian manifolds. Subsequently, we propose the pseudo-Riemannian Graph Transformer for learning representations of complex graph structures. Our diffeomorphic framework in pseudo-Riemannian geometry enables the principled definitions of core transformer components, including linear attention, residual connection, and layer normalization. Finally, we develop a lightweight space searching algorithm to automatically identify the most suitable pseudo-Riemannian manifold for an input graph. Extensive experiments on diverse real-world graphs demonstrate that our model consistently outperforms other baselines in both node classification and link prediction tasks.

Dynamic graph learning is a rapidly developing area of research due to its widespread application in various real-world networks. Most existing works combine graph neural networks and sequential models to exploit the graph topology and the temporal information of dynamic graphs. However, these methods exhibit certain limitations in extracting local and global information and capturing fine-grained temporal structure in dynamic graphs. In this article, we present our novel framework, Dynamic Graph Subtree Attention, which is centralized by a learnable temporal edge sampling module and a lightweight attention operator to address the aforementioned issues. Our approach first constructs a temporal union graph for each time step using an adaptive edge sampling module, which preserves relevant interactions for our graph encoder to directly exploit fine-gained interactions across different times. Based on the temporal union graph, we further propose a subtree attention module that leverages the multi-hop representation and the self-attention mechanism to properly extract the local and global information from first- to high-order neighborhoods. To further reduce the computation complexity, the subtree module is equipped with a kernelized attention operation, which scales linearly with respect to the number of edges. By performing extensive experiments, we demonstrate the superiority of our proposed model in dynamic graph representation learning, as it consistently outperforms existing methods in future link prediction tasks. The code is publicly available at: https://github.com/minhduc1122002/DySubTree .

Soft actor-critic (SAC) is a reinforcement learning algorithm that employs the maximum entropy framework to train a stochastic policy. This work examines a specific failure case of SAC where the stochastic policy is trained to maximize the expected entropy from a sparse reward environment. We demonstrate that the over-exploration of SAC can make the entropy temperature collapse, followed by unstable updates to the actor. Based on our analyses, we introduce Reg-SAC, an improved version of SAC, to mitigate the detrimental effects of the entropy temperature on the learning stability of the stochastic policy. Reg-SAC incorporates a clipping value to prevent the entropy temperature collapse and regularizes the gradient updates of the policy via Kullback-Leibler divergence. Through experiments on discrete benchmarks, our proposed Reg-SAC outperforms the standard SAC in spare-reward grid world environments while it is able to maintain competitive performance in the dense-reward Atari benchmark. The results highlight that our regularized version makes the stochastic policy of SAC more stable in discrete-action domains.

In multitask reinforcement learning, tasks often have sub-tasks that share the same solution, even though the overall tasks are different. If the shared-portions could be effectively identified, then the learning process could be improved since all the samples between tasks in the shared space could be used. In this paper, we propose a Sharing Experience Framework (SEF) for simultaneously training of multiple tasks. In SEF, a confidence sharing agent uses task-specific rewards from the environment to identify similar parts that should be shared across tasks and defines those parts as shared-regions between tasks. The shared-regions are expected to guide task-policies sharing their experience during the learning process. The experiments highlight that our framework improves the performance and the stability of learning task-policies, and is possible to help task-policies avoid local optimums.

In a multi-user context, the Bluetooth data from the smartphone could give an approximation of the distance between users. Meanwhile, the Wi-Fi data can be used to calculate the user's position directly. However, both the Wi-Fi-based position outputs and Bluetooth-based distances are affected by some degree of noise. In our work, we propose several approaches to combine the two types of outputs for improving the tracking accuracy in the context of collaborative positioning. The two proposed approaches attempt to build a model for measuring the errors of the Bluetooth output and Wi-Fi output. In a non-temporal approach, the model establishes the relationship in a specific interval of the Bluetooth output and Wi-Fi output. In a temporal approach, the error measurement model is expanded to include the time component between users' movement. To evaluate the performance of the two approaches, we collected the data from several multi-user scenarios in indoor environment. The results show that the proposed approaches could reach a distance error around 3.0m for 75 percent of time, which outperforms the positioning results of the standard Wi-Fi fingerprinting model.

This paper introduces our work in the framework of Track 3 of the IPIN 2016 Indoor Localization Competition, which addresses the smartphone-based tracking problem in an offline manner. Our approach splits the path-reconstruction into several smaller tasks, including building identification, floor identification, user direction and speed inference. For each task, a specific set of data from the provided log data is used. Evaluation is carried out using a cross validation scheme. To produce the robustness again noisy data, we combine several approaches into one on the basis of their testing results. By testing on the provided training data, we have a good accuracy on building and floor identification. For the task of tracking the user's position within the floor, the result is 10m at 3rd-quarter distance error after 3 minutes of walking.

New technologies and especially robotics is going towards more natural user interfaces. Works have been done in different modality of interaction such as sight (visual computing), and audio (speech and audio recognition) but some other modalities are still less researched. The touch modality is one of the less studied in HRI but could be valuable for naturalistic interaction. However touch signals can vary in semantics. It is therefore necessary to be able to recognize touch gestures in order to make human-robot interaction even more natural. We propose a method to recognize touch gestures. This method was developed on the CoST corpus and then directly applied on the HAART dataset as a participation of the Social Touch Challenge at ICMI 2015. Our touch gesture recognition process is detailed in this article to make it reproducible by other research teams. Besides features set description, we manually filtered the training corpus to produce 2 datasets. For the challenge, we submitted 6 different systems. A Support Vector Machine and a Random Forest classifiers for the HAART dataset. For the CoST dataset, the same classifiers are tested in two conditions: using all or filtered training datasets. As reported by organizers, our systems have the best correct rate in this year's challenge (70.91% on HAART, 61.34% on CoST). Our performances are slightly better that other participants but stay under previous reported state-of-the-art results.