Yanming Shen
YOU?
Author Swipe
View article: Bridging Molecular Graphs and Large Language Models
Bridging Molecular Graphs and Large Language Models Open
While Large Language Models (LLMs) have shown exceptional generalization capabilities, their ability to process graph data, such as molecular structures, remains limited. To bridge this gap, this paper proposes Graph2Token, an efficient so…
View article: Bridging Molecular Graphs and Large Language Models
Bridging Molecular Graphs and Large Language Models Open
While Large Language Models (LLMs) have shown exceptional generalization capabilities, their ability to process graph data, such as molecular structures, remains limited. To bridge this gap, this paper proposes Graph2Token, an efficient so…
View article: Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Things
Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Things Open
With the advancement of information technology, the Social Internet of Things (SIoT) has fostered the integration of physical devices and social networks, deepening the study of complex interaction patterns. Text Attribute Graphs (TAGs) ca…
View article: Consistent RNA expression and RNA modification patterns in cardiotoxicity induced by Matrine and Evodiamine
Consistent RNA expression and RNA modification patterns in cardiotoxicity induced by Matrine and Evodiamine Open
Recent research has demonstrated the efficacy of traditional Chinese medicine (TCM) and its active compounds in combating cancer, leading to an increasing utilization of TCM as adjunctive therapy in clinical oncology. However, the optimal …
View article: Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning
Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning Open
Graphs are data structures used to represent irregular networks and are prevalent in numerous real-world applications. Previous methods directly model graph structures and achieve significant success. However, these methods encounter bottl…
View article: Mdpm: Modulating Domain-Specific Prompt Memory for Multi-Domain Traffic Flow Prediction with Transformers
Mdpm: Modulating Domain-Specific Prompt Memory for Multi-Domain Traffic Flow Prediction with Transformers Open
View article: Temperature Control Performance and Cooling Release Characteristics of PCM in Large Space: Case Study of Cold Storage
Temperature Control Performance and Cooling Release Characteristics of PCM in Large Space: Case Study of Cold Storage Open
View article: Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization
Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization Open
Recent advances in knowledge graph embedding (KGE) rely on Euclidean/hyperbolic orthogonal relation transformations to model intrinsic logical patterns and topological structures. However, existing approaches are confined to rigid relation…
View article: TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation
TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation Open
Next Point-of-Interest (POI) recommendation has been proven effective at utilizing sparse, intricate spatial-temporal trajectory data to recommend subsequent POIs to users. While existing methods commonly alleviate the problem of data spar…
View article: Temperature Control Performance and Cooling Releasing Characteristics of Pcm in Large Space: Case Study of Cold Storage
Temperature Control Performance and Cooling Releasing Characteristics of Pcm in Large Space: Case Study of Cold Storage Open
View article: The Effects of Thickness and Location of PCM on the Building’s Passive Temperature-Control–A Numerical Study
The Effects of Thickness and Location of PCM on the Building’s Passive Temperature-Control–A Numerical Study Open
Building energy consumption and building carbon emissions both account for more than 20% of their total national values in China. Building employing phase change material (PCM) for passive temperature control shows a promising prospect in …
View article: To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion Open
Embedding models have shown great power in knowledge graph completion (KGC) task. By learning structural constraints for each training triple, these methods implicitly memorize intrinsic relation rules to infer missing links. However, this…
View article: Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering Open
Proposing an effective and flexible matrix to represent a graph is a fundamental challenge that has been explored from multiple perspectives, e.g., filtering in Graph Fourier Transforms. In this work, we develop a novel and general framewo…
View article: To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion Open
Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 20…
View article: NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction
NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction Open
Recently, deep learning methods have made great progress in traffic prediction, but their performance depends on a large amount of historical data. In reality, we may face the data scarcity issue. In this case, deep learning models fail to…
View article: HousE: Knowledge Graph Embedding with Householder Parameterization
HousE: Knowledge Graph Embedding with Householder Parameterization Open
The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties. However, existing approaches can only capture some of them with insufficient modeling capacity…
View article: A New Perspective on the Effects of Spectrum in Graph Neural Networks
A New Perspective on the Effects of Spectrum in Graph Neural Networks Open
Many improvements on GNNs can be deemed as operations on the spectrum of the underlying graph matrix, which motivates us to directly study the characteristics of the spectrum and their effects on GNN performance. By generalizing most exist…
View article: First Place Solution of KDD Cup 2021 OGB Large-Scale Challenge Graph-Level Track
First Place Solution of KDD Cup 2021 OGB Large-Scale Challenge Graph-Level Track Open
In this technical report, we present our solution of KDD Cup 2021 OGB
Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our
basic models. We train each model by 8-fold cross-validation, and additionally
train two Gr…
View article: First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track.
First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track. Open
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models. We train each model by 8-fold cross-validation, and additionally train two Gr…
View article: First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track
First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track Open
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our basic models. We train each model by 8-fold cross-validation, and additionally train two Gr…
View article: Awardee Solution of KDD Cup 2021 OGB Large-Scale Challenge Graph-Level Track
Awardee Solution of KDD Cup 2021 OGB Large-Scale Challenge Graph-Level Track Open
In this technical report, we present our solution of KDD Cup 2021 OGB
Large-Scale Challenge - PCQM4M-LSC Track. We adopt Graphormer and ExpC as our
basic models. We train each model by 8-fold cross-validation, and additionally
train two Gr…
View article: Do Transformers Really Perform Bad for Graph Representation?
Do Transformers Really Perform Bad for Graph Representation? Open
The Transformer architecture has become a dominant choice in many domains, such as natural language processing and computer vision. Yet, it has not achieved competitive performance on popular leaderboards of graph-level prediction compared…
View article: Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks
Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks Open
For learning graph representations, not all detailed structures within a\ngraph are relevant to the given graph tasks. Task-relevant structures can be\n$localized$ or $sparse$ which are only involved in subgraphs or characterized\nby the i…
View article: Breaking the Expressive Bottlenecks of Graph Neural Networks
Breaking the Expressive Bottlenecks of Graph Neural Networks Open
Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in distinguishing grap…
View article: A Comprehensive Survey on Traffic Prediction.
A Comprehensive Survey on Traffic Prediction. Open
Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the compl…
View article: Enhanced Visible-Light-Driven Photocatalytic Activity of ZnAl Layered Double Hydroxide by Incorporation of Co2+
Enhanced Visible-Light-Driven Photocatalytic Activity of ZnAl Layered Double Hydroxide by Incorporation of Co2+ Open
Co-doped ZnAl layered double hydroxides (LDH) were papered by coprecipitation. The prepared samples were characterized by multiple techniques including X-ray Diffraction (XRD), Brunauer−Emmett−Teller (BET) surface area, Scanning Electronic…
View article: Liquid-phase Hydrogenation of Phenol to Cyclohexanone over Supported Palladium Catalysts
Liquid-phase Hydrogenation of Phenol to Cyclohexanone over Supported Palladium Catalysts Open
The ZSM-5, g-Al2O3, SiO2 and MgO supported Pd-catalysts were prepared for the phenol hydrogenation to cyclohexanone in liquid-phase. The natures of these catalysts were characterized by XRD, N2 adsorption-desorption analysis, H2-TPR, CO2-T…
View article: Measurement and Prediction of Hydrate Phase Equilibrium of Orange Juice + CO2, C2H4 or C2H6 for Orange Juice Concentration
Measurement and Prediction of Hydrate Phase Equilibrium of Orange Juice + CO2, C2H4 or C2H6 for Orange Juice Concentration Open
Phase equilibrium data for hydrates formed in CO 2 + orange juice system, C 2 H 4 + orange juice system and C 2 H 6 + orange juice system were measured in pressures range of (0.68 to 4.40 MPa) and temperatures range of (274.8 to 283.3 K…
View article: Job-aware Network Scheduling for Hadoop Cluster
Job-aware Network Scheduling for Hadoop Cluster Open
In recent years, data centers have become the core infrastructure to deal with big data processing.For these big data applications, network transmission has become one of the most important factors affecting the performance.In order to imp…