Dawei Cheng
YOU?
Author Swipe
View article: FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design
FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design Open
Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimodal reasoning datasets and the inefficiency of existing train…
View article: CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model
CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model Open
Multimodal Large Language Models (MLLMs) have rapidly evolved with the growth of Large Language Models (LLMs) and are now applied in various fields. In finance, the integration of diverse modalities such as text, charts, and tables is cruc…
View article: Language Model-Enhanced Message Passing for Heterophilic Graph Learning
Language Model-Enhanced Message Passing for Heterophilic Graph Learning Open
Traditional graph neural networks (GNNs), which rely on homophily-driven message passing, struggle with heterophilic graphs where connected nodes exhibit dissimilar features and different labels. While existing methods address heterophily …
View article: Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study
Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study Open
Nowadays, real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge without forgetting previously learned information. Although substa…
View article: Efficient Learning-Based Graph Simulation for Temporal Graphs
Efficient Learning-Based Graph Simulation for Temporal Graphs Open
Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal …
View article: Multi-Granularity Augmented Graph Learning for Spoofing Transaction Detection
Multi-Granularity Augmented Graph Learning for Spoofing Transaction Detection Open
View article: Dual Pairwise Pre-training and Prompt-tuning with Aligned Prototypes for Interbank Credit Rating
Dual Pairwise Pre-training and Prompt-tuning with Aligned Prototypes for Interbank Credit Rating Open
View article: Generative Dynamic Graph Representation Learning for Conspiracy Spoofing Detection
Generative Dynamic Graph Representation Learning for Conspiracy Spoofing Detection Open
Spoofing detection in financial trading is crucial, especially for identifying complex behaviors such as conspiracy spoofing. Traditional machine-learning approaches primarily focus on isolated node features, often overlooking the broader …
View article: Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection
Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection Open
View article: Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting Open
Transformer-based and MLP-based methods have emerged as leading approaches in time series forecasting (TSF). However, real-world time series often show different patterns at different scales, and future changes are shaped by the interplay …
View article: Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks Open
Graph Neural Networks (GNNs) demonstrate superior performance in various graph learning tasks, yet their wider real-world application is hindered by the computational overhead when applied to large-scale graphs. To address the issue, the G…
View article: FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting
FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting Open
Financial time series (FinTS) record the behavior of human-brain-augmented decision-making, capturing valuable historical information that can be leveraged for profitable investment strategies. Not surprisingly, this area has attracted con…
View article: MasRouter: Learning to Route LLMs for Multi-Agent Systems
MasRouter: Learning to Route LLMs for Multi-Agent Systems Open
Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often incur significant costs and face challenges in dynamic LLM selection. Current LLM routing m…
View article: FinMamba: Market-Aware Graph Enhanced Multi-Level Mamba for Stock Movement Prediction
FinMamba: Market-Aware Graph Enhanced Multi-Level Mamba for Stock Movement Prediction Open
Recently, combining stock features with inter-stock correlations has become a common and effective approach for stock movement prediction. However, financial data presents significant challenges due to its low signal-to-noise ratio and the…
View article: TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting Open
Time series forecasting methods generally fall into two main categories: Channel Independent (CI) and Channel Dependent (CD) strategies. While CI overlooks important covariate relationships, CD captures all dependencies without distinction…
View article: MasRouter: Learning to Route LLMs for Multi-Agent Systems
MasRouter: Learning to Route LLMs for Multi-Agent Systems Open
View article: Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool Open
\textbf{G}raph \textbf{N}eural \textbf{N}etworks~(GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their vulnerabili…
View article: Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks Open
Graph Neural Networks (GNNs) demonstrate superior performance in various graph learning tasks, yet their wider real-world application is hindered by the computational overhead when applied to large-scale graphs. To address the issue, the G…
View article: GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning Open
Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by r…
View article: G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks Open
Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologi…
View article: TCGU: Data-centric Graph Unlearning based on Transferable Condensation
TCGU: Data-centric Graph Unlearning based on Transferable Condensation Open
With growing demands for data privacy and model robustness, graph unlearning (GU), which erases the influence of specific data on trained GNN models, has gained significant attention. However, existing exact unlearning methods suffer from …
View article: Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems Open
Recent advancements in large language model (LLM)-powered agents have shown that collective intelligence can significantly outperform individual capabilities, largely attributed to the meticulously designed inter-agent communication topolo…
View article: MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU
MCI-GRU: Stock Prediction Model Based on Multi-Head Cross-Attention and Improved GRU Open
As financial markets grow increasingly complex in the big data era, accurate stock prediction has become more critical. Traditional time series models, such as GRUs, have been widely used but often struggle to capture the intricate nonline…
View article: LSR-IGRU: Stock Trend Prediction Based on Long Short-Term Relationships and Improved GRU
LSR-IGRU: Stock Trend Prediction Based on Long Short-Term Relationships and Improved GRU Open
Stock price prediction is a challenging problem in the field of finance and receives widespread attention. In recent years, with the rapid development of technologies such as deep learning and graph neural networks, more research methods h…
View article: PAMol: Pocket-Aware Drug Design Method with Hypergraph Representation of Protein Pocket Structure and Feature Fusion
PAMol: Pocket-Aware Drug Design Method with Hypergraph Representation of Protein Pocket Structure and Feature Fusion Open
Efficient generation of targeted drug molecules is crucial in the field of drug discovery. Most existing methods neglect the high-order information in the structure of protein pockets, limiting the performance of generated drug molecules. …
View article: Establishment of an A/T-Rich Specifically MGB Probe digital droplet PCR Assays Based on SNP for Brucella wild strains and vaccine strains
Establishment of an A/T-Rich Specifically MGB Probe digital droplet PCR Assays Based on SNP for Brucella wild strains and vaccine strains Open
In recent years, immunization with the S2 live-attenuated vaccine has been recognized as the most economical and effective strategy for preventing brucellosis in Inner Mongolia, China. However, there are still challenges related to vaccine…
View article: Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting Open
Transformer-based and MLP-based methods have emerged as leading approaches in time series forecasting (TSF). While Transformer-based methods excel in capturing long-range dependencies, they suffer from high computational complexities and t…
View article: Hypergraph Self-supervised Learning with Sampling-efficient Signals
Hypergraph Self-supervised Learning with Sampling-efficient Signals Open
Self-supervised learning (SSL) provides a promising alternative for representation learning on hypergraphs without costly labels. However, existing hypergraph SSL models are mostly based on contrastive methods with the instance-level discr…
View article: Pre-trained Online Contrastive Learning for Insurance Fraud Detection
Pre-trained Online Contrastive Learning for Insurance Fraud Detection Open
Medical insurance fraud has always been a crucial challenge in the field of healthcare industry. Existing fraud detection models mostly focus on offline learning scenes. However, fraud patterns are constantly evolving, making it difficult …
View article: Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection Open
Graph-based anomaly detection is currently an important research topic in the field of graph neural networks (GNNs). We find that in graph anomaly detection, the homophily distribution differences between different classes are significantl…