Author name cluster

Zheng Hu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2025 Conference Paper

Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models

Zheng Hu
Zhe Li
Ziyun Jiao
Satoshi Nakagawa
Jiawen Deng
Shimin Cai
Tao Zhou
Fuji Ren

In recent years, knowledge graphs have been integrated into recommender systems as item-side auxiliary information, enhancing recommendation accuracy. However, constructing and integrating structural user-side knowledge remains a significant challenge due to the improper granularity and inherent scarcity of user-side features. Recent advancements in Large Language Models (LLMs) offer the potential to bridge this gap by leveraging their human behavior understanding and extensive real-world knowledge. Nevertheless, integrating LLM-generated information into recommender systems presents challenges, including the risk of noisy information and the need for additional knowledge transfer. In this paper, we propose an LLM-based user-side knowledge inference method alongside a carefully designed recommendation framework to address these challenges. Our approach employs LLMs to infer user interests based on historical behaviors, integrating this user-side information with item-side and collaborative data to construct a hybrid structure: the Collaborative Interest Knowledge Graph (CIKG). Furthermore, we propose a CIKG-based recommendation framework that includes a user interest reconstruction module and a cross-domain contrastive learning module to mitigate potential noise and facilitate knowledge transfer. We conduct extensive experiments on three real-world datasets to validate the effectiveness of our method. Our approach achieves state-of-the-art performance compared to competitive baselines, particularly for users with sparse interactions.

PDF Details DOI

AAAI Conference 2025 Conference Paper

SSL-STMFormer Self-Supervised Learning Spatio-Temporal Entanglement Transformer for Traffic Flow Prediction

Zetao Li
Zheng Hu
Peng Han
Yu Gu
Shimin Cai

Traffic flow prediction remains a critical issue in intelligent transport systems. Despite significant efforts in traffic flow modeling, existing approaches exhibit several notable limitations: (i) Most models fail to capture traffic flow similarities over long distances and extended periods; (ii) They struggle to account for spatio-temporal heterogeneity induced by varying traffic flow patterns; (iii) Due to their static modeling approach, they struggle to effectively capture the intricate spatio-temporal entanglement. To address these challenges, we propose a traffic flow prediction framework based on self-supervised learning spatio-temporal entanglement transformer(SSL-STMFormer). This framework adopts a self-supervised learning paradigm, leveraging a transformer architecture that captures richer spatio-temporal information to better represent traffic flow patterns. Specifically, a temporal attention module and a spatial attention module are employed to capture the spatio-temporal dependencies of traffic dynamics, respectively, and spatio-temporal entanglement-aware methods are introduced to allow the model to perceive spatio-temporal entanglement and thus better modelling of real traffic environments. Furthermore, to achieve adaptive spatio-temporal self-supervised learning, adaptive data augmentation is applied to the input traffic flow data, and the traffic flow prediction task is enhanced with temporal heterogeneity module and spatial heterogeneity module. Extensive experimental evaluations conducted on six publicly available real-world transportation datasets demonstrate that our method achieves substantial improvements across these datasets.

PDF Details DOI

AAAI Conference 2025 Conference Paper

WEPO: Web Element Preference Optimization for LLM-based Web Navigation

Jiarun Liu
Jia Hao
Chunhong Zhang
Zheng Hu

The rapid advancement of autonomous web navigation has significantly benefited from grounding pretrained Large Language Models (LLMs) as agents. However, current research has yet to fully leverage the redundancy of HTML elements for contrastive training. This paper introduces a novel approach to LLM-based web navigation tasks, called Web Element Preference Optimization (WEPO). WEPO utilizes unsupervised preference learning by sampling distance-based non-salient web elements as negative samples, optimizing maximum likelihood objective within Direct Preference Optimization (DPO). We evaluate WEPO on the Mind2Web benchmark and empirically demonstrate that WEPO aligns user high-level intent with output actions more effectively. The results show that our method achieved the state-of-the-art, with an improvement of 13.8% over WebAgent and 5.3% over the visual language model CogAgent baseline. Our findings underscore the potential of preference optimization to enhance web navigation and other web page based tasks, suggesting a promising direction for future research.

PDF Details DOI

AAMAS Conference 2023 Conference Paper

Hierarchical Reinforcement Learning with Attention Reward

Sihong Luo
Jinghao Chen
Zheng Hu
Chunhong Zhang
Benhui Zhuang

Hierarchical Reinforcement Learning (HRL) is a promising approach for complex tasks with greater sample efficiency because it can break a task into sets of short subtasks and provide a denser subgoal-related intrinsic reward, making credit assignments less challenging. However, none of the conventional subgoal-related intrinsic rewards utilize task-specified knowledge, which limits the sample efficiency of these HRL methods. We propose Hierarchical Reinforcement Learning with Attention Reward (HiAR) that motivates agents to focus on the part of the environment controlled by their actions. We introduce a measure of the control over each dimension in the state space and discuss how we integrated it into the HRL method to improve the sample efficiency.

PDF

AAAI Conference 2023 Conference Paper

PatchNAS: Repairing DNNs in Deployment with Patched Network Architecture Search

Yuchu Fang
Wenzhong Li
Yao Zeng
Yang Zheng
Zheng Hu
Sanglu Lu

Despite being widely deployed in safety-critical applications such as autonomous driving and health care, deep neural networks (DNNs) still suffer from non-negligible reliability issues. Numerous works had reported that DNNs were vulnerable to either natural environmental noises or man-made adversarial noises. How to repair DNNs in deployment with noisy samples is a crucial topic for the robustness of neural networks. While many network repairing methods based on data argumentation and weight adjustment have been proposed, they require retraining and redeploying the whole model, which causes high overhead and is infeasible for varying faulty cases on different deployment environments. In this paper, we propose a novel network repairing framework called PatchNAS from the architecture perspective, where we freeze the pretrained DNNs and introduce a small patch network to deal with failure samples at runtime. PatchNAS introduces a novel network instrumentation method to determine the faulty stage of the network structure given the collected failure samples. A small patch network structure is searched unsupervisedly using neural architecture search (NAS) technique with data samples from deployment environment. The patch network repairs the DNNs by correcting the output feature maps of the faulty stage, which helps to maintain network performance on normal samples and enhance robustness in noisy environments. Extensive experiments based on several DNNs across 15 types of natural noises show that the proposed PatchNAS outperforms the state-of-the-arts with significant performance improvement as well as much lower deployment overhead.

PDF Details DOI

TCS Journal 2020 Journal Article

Distributed representation of knowledge graphs with subgraph-aware proximity

Xiao Han
Chunhong Zhang
Chenchen Guo
Yang Ji
Zheng Hu

The distributed representation of Knowledge graphs (KGs) aims to embed the original KG into a low-dimensional embedding vector space, so as to facilitate the completion of KGs as well as the application of KGs in other AI fields. Most existing models preserve certain proximity property of KGs in the embedding space, such as the first/second-order proximity and the sequence-aware higher-order proximity. However, the ubiquitous similarity relationship between different sequences has rarely been discussed. In this paper, we propose a unified framework to preserve the subgraph-aware proximity in the embedding space, holding that the sequences within a subgraph generally imply a similar pattern. Especially, according to the composition and structure of KG sequences, we provide three methods for computing the embeddings of KG sequences: 1) Simply adding the involved relations of the KG sequences in a relation subgraph; 2) Recurrent neural network for the KG sequences in a complete subgraph; 3) Dilated recurrent neural network to match the special structure of the KG sequences in a complete subgraph. Empirically, we evaluate the proposed framework on the KG completion tasks of link prediction and entity classification. The results show that our framework outperforms the baselines by preserving the subgraph-aware proximity. Especially, exploring the special structure of KG sequences can further improve the performance.

Details DOI

IROS Conference 2011 Conference Paper

Translational damping on flapping cicada wings

Perry Parks
Bo Cheng 0002
Zheng Hu
Xinyan Deng

We measured the dynamic damping of a pair of flapping cicada wings mounted on a robotic insect thorax mechanism capable of high frequency flapping. The damping coefficients were derived based on the measurements of the wing-thorax mechanism translating along its body principal axes. The robotic mechanism has a 10cm wingtip-to-wingtip span, flaps up to 65Hz, and weigh 2. 86 gram including the motor and wings. To measure the flapping induced damping during translation, we developed a pendulum system mounted with encoder, and attached the flapper at the end and in different orientations such that its motion is along its principle axes. The damping of the flapper is then calculated from the decaying rate of the magnitude of the oscillating pendulum. The damping coefficients calculated from the experiments are very close to those estimated based on our mathematic models using Blade-Element Theory (BET) and quasi-steady aerodynamic models. As expected, the damping linearly increases with the flapping frequency and is most prominent along forward/backward direction.

Details

ICRA Conference 2009 Conference Paper

Aerodynamics of dragonfly flight and robotic design

Zheng Hu
Raymond McCauley
Steve Schaeffer
Xinyan Deng

A pair of dynamically scaled robotic dragonfly model wings was developed to investigate the aerodynamic effect of wing-wing interaction in dragonfly flight. Instantaneous aerodynamic forces were measured while forewing-hindwing phase difference (gamma) was systematically varied. Experimental results showed that, (i) for hovering flight, gamma=0deg enhanced the lift force on both forewing and hindwing; gamma=180deg reduced the total lift force, but was beneficial for vibration suppression and body posture stabilization. In nature, 0deg is employed by dragonflies in acceleration mode while 180deg is usually in hovering mode. (ii) For forward flight, wing-wing interaction enhances forewing lift while reduced hindwing lift at all phase differences. Furthermore, the total lift was slightly reduced for gamma= 0deg to 90deg and significantly reduced by 18% when gamma=270deg. The results consist well with the fact that, dragonflies usually employ 50deg to 100deg for forward flight, but seldom employ 270deg. PIV results are shown for wing-wing interaction analysis.

Details