Author name cluster

Bowen Deng

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.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

Two Heads Are Better than One: Distilling Large Language Model Features into Small Models with Feature Decomposition and Mixture

Tianhao Fu
Xinxin Xu
Weichen Xu
Jue Chen
Ruilong Ren
Bowen Deng
Xinyu Zhao
Jian Cao

Market making (MM) through Reinforcement Learning (RL) has attracted significant attention in financial trading. With the development of Large Language Models (LLMs), more and more attempts are being made to apply LLMs to financial areas. A simple, direct application of LLM as an agent shows significant performance. Such methods are hindered by their slow inference speed, while most of the current research has not studied LLM distillation for this specific task. To address this, we first propose the normalized fluorescent probe to study the mechanism of the LLM’s feature. Based on the observation found by our investigation, we propose Cooperative Market Making (CMM), a novel framework that decouples LLM features across three orthogonal dimensions: layer, task, and data. Various student models collaboratively learn simple LLM features along with different dimensions, with each model responsible for a distinct feature to achieve knowledge distillation. Furthermore, CMM introduces an Hájek-MoE to integrate the output of the student models by investigating the contribution of different models in a kernel function-generated common feature space. Extensive experimental results on four real-world market datasets demonstrate the superiority of CMM over the current distillation method and RL-based market-making strategies.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

FedBG: Proactively Mitigating Bias in Cross-Domain Graph Federated Learning Using Background Data

Sheng Huang
Lele Fu
Tianchi Liao
Bowen Deng
Chuanfu Zhang
Chuan Chen

Federated graph learning is focused on aggregating knowledge from multi-source graph data and training graph neural networks. Unlike the data that traditional federated learning needs to deal with, federated graph learning also needs to face additional topological information. Further, there are also biases in features and topologies among clients, increasing the difficulty of training models. Previous methods usually seek global calibration information, however, this approach may suffer from information bias caused by data skews, and it is also difficult to naturally combine feature and topology information. Therefore, adjusting the bias before it occurs will hopefully address the learning difficulties caused by the skew. In view of this, we employ background graph data, which works as reference information for local training, to proactively correct bias before it occurs. As a kind of graph data, background graphs are naturally capable of combining feature and topology information to accomplish bias correction among clients in a comprehensive way. Mixing strategy is employed on the background graph to additionally provide privacy-preserving capabilities. Graph generation methods are employed to restore the diversity of background graphs that are blurred by the mixing strategy. Extensive experiments on two real-world datasets demonstrate the sufficient motivation and effectiveness of the proposed method.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Federated Domain Generalization with Decision Insight Matrix

Tianchi Liao
Binghui Xie
Lele Fu
Sheng Huang
Bowen Deng
Chuan Chen
Zibin Zheng

Federated domain generalization addresses the crucial challenge of developing models that can generalize across diverse domains while maintaining data privacy in federated learning settings. Current approaches either compromise privacy constraints or focus narrowly on specific aspects of model invariance, often incurring significant computational overhead. We propose a novel approach FedDIM, which leverages the concept of “insight matrix” - a fine-grained representation of the model's decision-making process derived from element-wise products between feature vectors and classifier weights. By introducing a regularization term that promotes consistency between individual sample insight matrices and their class-wise mean representations, our method effectively captures both feature and classifier invariance. This approach not only maintains strict privacy requirements but also introduces minimal computational overhead as it utilizes intermediate computations already present in the forward pass. Extensive experiments demonstrate that our method achieves superior out-of-distribution generalization compared to existing federated learning approaches while being simple to implement. Our work provides a new perspective on achieving robust generalization in federated learning settings through the lens of decision-making processes.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

GLNCD: Graph-Level Novel Category Discovery

Bowen Deng
Lele Fu
Sheng Huang
Tianchi Liao
Jialong Chen
Zhang Tao
Chuan Chen

Graph classification has long assumed a closed-world setting, limiting its applicability to real-world scenarios where new categories often emerge. To address this limitation, we introduce Graph-Level Novel Category Discovery (GLNCD), a new task aimed at identifying unseen graph categories without supervision from novel classes. We first adapt classical Novel Category Discovery (NCD) methods for images to the graph domain and evaluate these baseline methods on four diverse graph datasets curated for the GLNCD task. Our analysis reveals that these methods suffer a notable performance degradation compared to their image-based counterparts, due to two key challenges: (1) insufficient utilization of structural information in graph self-supervised learning (SSL), and (2) ineffective pseudo-labeling strategies based on ranking statistics (RS) that neglect graph structure. To alleviate these issues, we propose ProtoFGW-NCD, a framework consisting of two core components: ProtoFGW-CL, a novel graph SSL framework, and FGW-RS, a structure-aware pseudo-labeling method. Both components employ a differentiable Fused Gromov-Wasserstein (FGW) distance to effectively compare graphs by incorporating structural information. These components are built upon learnable prototype graphs, which enable efficient, parallel FGW-based graph comparisons and capture representative patterns within graph datasets. Experiments on four GLNCD benchmark datasets demonstrate the effectiveness of ProtoFGW-NCD.

PDF Details

IJCAI Conference 2025 Conference Paper

Learn from Global Rather Than Local: Consistent Context-Aware Representation Learning for Multi-View Graph Clustering

Lele Fu
Bowen Deng
Sheng Huang
Tianchi Liao
Chuanfu Zhang
Chuan Chen

Multi-view graph clustering (MVGC) has been of widespread interest owing to the ability of capturing the complementary information among views, thereby enhancing the performance of node clustering. Despite the impressive achievements of existing methods, they are limited by a common deficiency, namely, the curse of local manifold while failing to perceive the global manifold structure. In light of this drawback, we propose a Consistent Context-Aware Representation Learning (CCARL) method for MVGC, aiming to learn node representations from global space rather than just local topology. Concretely, we define a set of anchors to establish the global coordinate, which are optimally mapped to multi-view graphs with minimal cost via fused Gromov-Wasserstein optimal transport. To fuse the complementary information in various views, the attention mechanism is employed to integrate multiple graph embeddings into a consistent representation. By transforming to the global coordinate connecting with anchors, the consistent representation captures the contextual information, and its clustering-friendliness is further enhanced through a self-training strategy. Finally, extensive experiments on four multi-view graph datasets demonstrate the effectiveness of the proposed CCARL over existing MVGC methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

MIRA: Medical Time Series Foundation Model for Real-World Health Data

Hao Li
Bowen Deng
Chang Xu
ZhiYuan Feng
Viktor Schlegel
Yu-Hao Huang
Yizheng Sun
Jingyuan Sun

A unified foundation model for medical time series—pretrained on open access and ethically reviewed medical corpora—offers the potential to reduce annotation burdens, minimize model customization, and enable robust transfer across clinical institutions, modalities, and tasks, particularly in data-scarce or privacy-constrained environments. However, existing time series foundation models struggle to handle medical time series data due to its inherent challenges, including irregular intervals, heterogeneous sampling rates, and frequent missingness. To address these challenges, we introduce MIRA, a unified foundation model specifically designed for medical time series forecasting. MIRA incorporates a Continuous-Time Rotary Positional Encoding that enables fine-grained modeling of variable time intervals, a frequency-specific mixture-of-experts layer that routes computation across latent frequency regimes to further promote temporal specialization, and a Continuous Dynamics Extrapolation Block based on Neural ODE that models the continuous trajectory of latent states, enabling accurate forecasting at arbitrary target timestamps. Pretrained on a large-scale and diverse medical corpus comprising over 454 billion time points collect from publicly available datasets, MIRA achieving reductions in forecasting errors by an average of 8% and 6% in out-of-distribution and in-distribution scenarios, respectively. We also introduce a comprehensive benchmark spanning multiple downstream clinical tasks, establishing a foundation for future research in medical time series modeling.

PDF Details

NeurIPS Conference 2025 Conference Paper

Self-Assembling Graph Perceptrons

Jialong Chen
Tong Wang
Bowen Deng
Luonan Chen
Zibin Zheng
Chuan Chen

Inspired by the workings of biological brains, humans have designed artificial neural networks (ANNs), sparking profound advancements across various fields. However, the biological brain possesses high plasticity, enabling it to develop simple, efficient, and powerful structures to cope with complex external environments. In contrast, the superior performance of ANNs often relies on meticulously crafted architectures, which can make them vulnerable when handling complex inputs. Moreover, overparameterization often characterizes the most advanced ANNs. This paper explores the path toward building streamlined and plastic ANNs. Firstly, we introduce the Graph Perceptron (GP), which extends the most fundamental ANN, the Multi-Layer Perceptron (MLP). Subsequently, we incorporate a self-assembly mechanism on top of GP called Self-Assembling Graph Perceptron (SAGP). During training, SAGP can autonomously adjust the network's number of neurons and synapses and their connectivity. SAGP achieves comparable or even superior performance with only about 5% of the size of an MLP. We also demonstrate the SAGP's advantages in enhancing model interpretability and feature selection.

PDF Details

NeurIPS Conference 2025 Conference Paper

Soft-consensual Federated Learning for Data Heterogeneity via Multiple Paths

Sheng Huang
Lele Fu
Fanghua Ye
Tianchi Liao
Bowen Deng
Chuan Chen

Federated learning enables collaborative training while preserving the privacy of all participants. However, the heterogeneity in data distribution across multiple training nodes poses significant challenges to the construction of federated models. Prior studies were dedicated to mitigating the effects of data heterogeneity by using global information as a blueprint and restricting the local update of the model for reaching a "hard consensus". But this practice makes it difficult to balance local and global information, and it neglects to negotiate amicably between local and global models to reach mutually agreeable results, called ``soft consensus". In this paper, a multiple-path solving method is proposed to balance global and local features and combine these two feature preference paths to reach a soft consensus. Rather than relying on global information as the sole criterion, a negotiation process is employed to address the same objective by accommodating diverse feature preferences, thereby facilitating the discovery of a more plausible solution through multiple distinct pathways. Considering the overwhelming power of local features during local training, a swapping strategy is applied to weaken them to balance the solution paths. Moreover, to minimize the additional communication cost caused by the introduction of multiple paths, the solution of the task network is converted into data adaptation to reduce the amount of parameter transmission. Extensive experiments are conducted to demonstrate the advantages of the proposed method.

PDF Details

AAAI Conference 2025 Conference Paper

THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings

Bowen Deng
Tong Wang
Lele Fu
Sheng Huang
Chuan Chen
Tao Zhang

Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through self-supervised learning and then apply K-means to the encoder output. Some methods use this clustering result directly as the final assignment, while others initialize centroids based on this initial clustering and then finetune both the encoder and these learnable centroids. However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation. We summarize three reasons for the low cluster separability in existing methods: (1) lack of contextual information prevents discrimination between similar nodes from different clusters; (2) training tasks are not sufficiently aligned with the downstream clustering task; (3) the cluster information in the graph structure is not appropriately exploited. To address these issues, we propose conTrastive grapH clustEring by SwApping fUsed gRomov-wasserstein coUplingS (THESAURUS). Our method introduces semantic prototypes to provide contextual information, and employs a cross-view assignment prediction pretext task that aligns well with the downstream clustering task. Additionally, it utilizes Gromov-Wasserstein Optimal Transport (GW-OT) along with the proposed prototype graph to thoroughly exploit cluster information in the graph structure. To adapt to diverse real-world data, THESAURUS updates the prototype graph and the prototype marginal distribution in OT by using momentum. Extensive experiments demonstrate that THESAURUS achieves higher cluster separability than the prior art, effectively mitigating the Uniform Effect and Cluster Assimilation issues.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Unsupervised Federated Graph Learning

Lele Fu
Tianchi Liao
Sheng Huang
Bowen Deng
Shirui Pan
Chuan Chen

Federated graph learning (FGL) is a privacy-preserving paradigm for modeling distributed graph data, designed to train a powerful global graph neural network. Existing FGL methods predominantly rely on label information during training, effective FGL in an unsupervised setting remains largely unexplored territory. In this paper, we address two key challenges in unsupervised FGL: 1) Local models tend to converge in divergent directions due to the lack of shared semantic information across clients. Then, how to align representation spaces among multiple clients is the first challenge. 2) Conventional federated weighted aggregation easily results in degrading the performance of the global model, then which raises another challenge, namely how to adaptively learn the global model parameters. In response to the two questions, we propose a tailored framework named FedPAM, which is composed of two modules: Representation Space Alignment (RSA) and Adaptive Global Parameter Learning (AGPL). RSA leverages a set of learnable anchors to define the global representation space, then local subgraphs are aligned with them through the fused Gromov-Wasserstein optimal transport, achieving the representation space alignment across clients. AGPL stacks local model parameters into third-order tensors, and adaptively integrates the global model parameters in a low-rank tensor space, which facilitates to fuse the high-order knowledge among clients. Extensive experiments on eight graph datasets are conducted, the results demonstrate that the proposed FedPAM is superior over classical and SOTA compared methods.

PDF Details

EAAI Journal 2024 Journal Article

A denoising autoencoder based on U-Net and bidirectional long short-term memory for multi-level random telegraph signal analysis

Bowen Deng
HeeBong Yang
Na Young Kim

Random telegraph signals (RTSs) are specific time-fluctuating signal patterns marked by a series of distinctive switching events between well-defined signal levels. These signals are ubiquitous in many electronic, chemical, and biological devices and systems. Analyzing RTSs unveils associated system structures and internal operation mechanisms, offering valuable insights into performance sensitivity. Therefore, accurate parameter quantification of RTSs is essential for understanding their origin and significance. While two-level RTS analysis is straightforward, complications arise at multiple levels, especially with unwanted background fluctuations. To address this challenge, we developed a novel denoising autoencoder model with U-Net and bidirectional long short-term memory (DAE UBL) for denoising multi-level RTSs degraded by Gaussian white and pink noise. DAE UBL extracts lower-dimensional latent features with its encoder and reconstructs denoised RTS with its decoder. Trained and validated with large datasets of noisy multi-level RTSs, our DAE UBL demonstrates superior and stable denoising performance compared to four classic models with lower average median root mean squared errors by over 78% and 63% for all RTS data accompanying various strengths of white noise and pink noise. Average median signal-to-noise ratios in the DAE UBL analysis are increased by over 65% and 56% for the white noise and pink noise datasets. In the time domain, DAE UBL effectively suppresses both local and global fluctuations, thereby successfully removing background noise. Our model exhibits robust performance in denoising multi-level RTSs with strong pink noise. We envision that our DAE UBL will be an attractive denoising methodology for the complex multi-level RTS analysis.

Details DOI