arXiv subjects

Wenxin Xie

Publications and source records attributed to Wenxin Xie.

6 recordsLinked to original sources

arXiv2025

UniFucGrasp: Human-Hand-Inspired Unified Functional Grasp Annotation Strategy and Dataset for Diverse Dexterous Hands

Dexterous grasp datasets are vital for embodied intelligence, but mostly emphasize grasp stability, ignoring functional grasps needed for tasks like opening bottle caps or holding cup handles. Most rely on bulky, costly, and hard-to-control high-DOF Shadow Hands. Inspired by the human hand's underactuated mechanism, we establish UniFucGrasp, a universal functional grasp annotation strategy and dataset for multiple dexterous hand types. Based on biomimicry, it maps natural human motions to diverse hand structures and uses geometry-based force closure to ensure functional, stable, human-like grasps. This method supports low-cost, efficient collection of diverse, high-quality functional grasps. Finally, we establish the first multi-hand functional grasp dataset and provide a synthesis model to validate its effectiveness. Experiments on the UFG dataset, IsaacSim, and complex robotic tasks show that our method improves functional manipulation accuracy and grasp stability, demonstrates improved adaptability across multiple robotic hands, helping to alleviate annotation cost and generalization challenges in dexterous grasping. The project page is at https://haochen611.github.io/UFG.

cs.RO↗

arXiv2024

ENOVA: Autoscaling towards Cost-effective and Stable Serverless LLM Serving

Since the increasing popularity of large language model (LLM) backend systems, it is common and necessary to deploy stable serverless serving of LLM on multi-GPU clusters with autoscaling. However, there exist challenges because the diversity and co-location of applications in multi-GPU clusters will lead to low service quality and GPU utilization. To address them, we build ENOVA, a deployment, monitoring and autoscaling service towards serverless LLM serving. ENOVA deconstructs the execution process of LLM service comprehensively, based on which ENOVA designs a configuration recommendation module for automatic deployment on any GPU clusters and a performance detection module for autoscaling. On top of them, ENOVA implements a deployment execution engine for multi-GPU cluster scheduling. The experiment results show that ENOVA significantly outperforms other state-of-the-art methods and is suitable for wide deployment in large online systems.

cs.DC↗

arXiv2023

Betweenness Approximation for Edge Computing with Hypergraph Neural Network

Edge computing is highly demanded to achieve their full potentials Internet of Things (IoT), since various IoT systems have been generating big data facilitating modern latency-sensitive applications. As a basic problem, network dismantling tries to find an optimal set of nodes of which will maximize the connectivity degradation in a network. However, current approaches mainly focus on simple networks modeling only pairwise interactions between two nodes, while higher order groupwise interactions among arbitrary number of nodes are ubiquitous in real world which can be better modeled as hypernetwork. The structural difference between simple network and hypernetwork restricts the direct application of simple network dismantling methods to hypernetwork. Even though some hypernetwork centrality measures such as betweenness can be used for hypernetwork dismantling, they face the problem of balancing effectiveness and efficiency. Therefore, we propose a betweenness approximation-based hypernetwork dismantling method with hypergraph neural network, namely HND. HND trains a transferable hypergraph neural network-based regression model on plenty of generated small-scale synthetic hypernetwork in a supervised way, and utilizes the well-trained model to approximate nodes' betweenness. Extensive experiments on five real hypernetworks demonstrate the effectiveness and efficiency of HND comparing with various baselines.

cs.SI↗

arXiv2022

Hypernetwork Dismantling via Deep Reinforcement Learning

Network dismantling aims to degrade the connectivity of a network by removing an optimal set of nodes. It has been widely adopted in many real-world applications such as epidemic control and rumor containment. However, conventional methods usually focus on simple network modeling with only pairwise interactions, while group-wise interactions modeled by hypernetwork are ubiquitous and critical. In this work, we formulate the hypernetwork dismantling problem as a node sequence decision problem and propose a deep reinforcement learning (DRL)-based hypernetwork dismantling framework. Besides, we design a novel inductive hypernetwork embedding method to ensure the transferability to various real-world hypernetworks. Our framework first generates small-scale synthetic hypernetworks and embeds the nodes and hypernetworks into a low dimensional vector space to represent the action and state space in DRL, respectively. Then trial-and-error dismantling tasks are conducted by an agent on these synthetic hypernetworks, and the dismantling strategy is continuously optimized. Finally, the well-optimized strategy is applied to real-world hypernetwork dismantling tasks. Experimental results on five real-world hypernetworks demonstrate the effectiveness of our proposed framework.

cs.LG↗

arXiv2022

Heterogeneous Information Network-based Interest Composition with Graph Neural Network for Recommendation

Heterogeneous information networks (HINs) are widely applied to recommendation systems due to their capability of modeling various auxiliary information with meta-paths. However, existing HIN-based recommendation models usually fuse the information from various meta-paths by simple weighted sum or concatenation, which limits performance improvement because it lacks the capability of interest compositions among meta-paths. In this article, we propose an HIN-based Interest Composition model for Recommendation (HicRec). Specifically, user and item representations are learned with a graph neural network on both the graph structure and features in each meta-path, and a parameter sharing mechanism is utilized here to ensure that the user and item representations are in the same latent space. Then, users' interests in each item from each pair of related meta-paths are calculated by a combination of the user and item representations. The composed user interests are obtained by their single interest from both intra- and inter-meta-paths for recommendation. Extensive experiments are conducted on three real-world datasets and the results demonstrate that our proposed HicRec model outperforms the baselines.

cs.IR↗

arXiv2022

Session-based Social and Dependency-aware Software Recommendation

With the increase of complexity of modern software, social collaborative coding and reuse of open source software packages become more and more popular, which thus greatly enhances the development efficiency and software quality. However, the explosive growth of open source software packages exposes developers to the challenge of information overload. While this can be addressed by conventional recommender systems, they usually do not consider particular constraints of social coding such as social influence among developers and dependency relations among software packages. In this paper, we aim to model the dynamic interests of developers with both social influence and dependency constraints, and propose the Session-based Social and Dependency-aware software Recommendation (SSDRec) model. This model integrates recurrent neural network (RNN) and graph attention network (GAT) into a unified framework. An RNN is employed to model the short-term dynamic interests of developers in each session and two GATs are utilized to capture social influence from friends and dependency constraints from dependent software packages, respectively. Extensive experiments are conducted on real-world datasets and the results demonstrate that our model significantly outperforms the competitive baselines.

cs.IR↗