Zheng Chen

AAAI Conference 2026 Conference Paper

A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication

• Angelo Rodio
• Giovanni Neglia
• Zheng Chen
• Erik G. Larsson

In semi-decentralized federated learning, devices primarily rely on device-to-device communication but occasionally interact with a central server. Periodically, a sampled subset of devices uploads their local models to the server, which computes an aggregate model. The server can then either (i) share this aggregate model only with the sampled clients (sampled-to-sampled, S2S) or (ii) broadcast it to all clients (sampled-to-all, S2A). Despite their practical significance, a rigorous theoretical and empirical comparison of these two strategies remains absent. We address this gap by analyzing S2S and S2A within a unified convergence framework that accounts for key system parameters: sampling rate, server aggregation frequency, and network connectivity. Our results, both analytical and experimental, reveal distinct regimes where one strategy outperforms the other, depending primarily on the degree of data heterogeneity across devices. These insights lead to concrete design guidelines for practical semi-decentralized FL deployments.

JBHI Journal 2026 Journal Article

Developing Dynamic Prediction Methods for Survival Time Lost in Chronic Kidney Disease Progression under Competing Risks

• Haoning Shen
• Chengfeng Zhang
• Xingzhi Wang
• Di Xie
• Shuyu Chen
• Pansheng Xue
• Yuanying Chen
• Yawen Hou

Patients with chronic kidney disease (CKD) may progress to end-stage renal disease (ESRD) or die from other causes during long-term follow-up, making it essential to properly account for competing risks in prognostic modeling. However, most existing CKD prediction models rely on hazard-based measures, which primarily reflect relative effects, lack clinical interpretability, and cannot directly quantify survival time lost due to disease progression or death. To address this limitation, we adopted the restricted mean time lost (RMTL), an absolute and intuitive measure of survival time loss, and developed a dynamic prediction model under competing risks. Given the rich time-dependent covariate information in longitudinal CKD data and the clinical need for patients to understand their disease progression at different stages, we developed a dynamic RMTL prediction model that incorporates the landmark approach. The model captures how covariate effects evolve over time, offering insights into the dynamic impact of clinical variables, and enables individualized prediction of survival time loss over a future window from any given prediction time point. We evaluated its statistical properties through Monte Carlo simulations and demonstrated its practical utility using CKD patient data from the AASK cohort. The results showed that the proposed model yields accurate and robust estimates, captures time-varying covariate effects, and outperforms conventional static models in predictive performance. By quantifying survival time loss under competing risks, the dynamic RMTL model offers clinically interpretable and individualized risk estimates, supporting personalized risk assessment and intervention planning in chronic disease management.

EAAI Journal 2026 Journal Article

Quantitative assessment of interfacial debonding in large-span concrete-filled steel tube arch bridges via interpretable deep hybrid learning and ultrasonic inspection

• Minghui Yao
• Shuhong Guan
• Jing Li
• Zheng Chen
• Junhui Liu
• Cai Tan
• Yunchao Tang

Interfacial debonding between the steel tube and concrete core poses a critical threat to the structural integrity and serviceability of concrete-filled steel tube (CFST) arch bridges. However, the occult nature of such internal defects, obscured by the external steel wall, complicates traditional inspection and quantitative assessment. This study proposes an intelligent non-destructive testing (NDT) framework integrating ultrasonic wave propagation with a deep hybrid learning architecture. Specifically, an improve deep hybrid learning model was developed to achieve high-precision quantification of debonding severity. The model leverages convolutional neural networks (CNN) for spatial feature extraction from ultrasonic signals, bidirectional long short-term memory (BiLSTM) for capturing bidirectional temporal dependencies, and an attention mechanism to adaptively weight salient features. Experimental results demonstrate superior predictive accuracy on the test set, achieving an R-squared of 0. 93, with a Root Mean Square Error of 4. 69 and Mean Absolute Error of 3. 72. To address the inherent opacity of the model, a SHapley Additive exPlanation (SHAP) framework was implemented, quantifying the contributory impact of key input parameters on the predictions. Field validation via core sampling on an in-service CFST arch bridge further confirmed the model's robust generalization capability (R-squared of 0. 89). The findings provide a scientific basis for the automated, quantitative health monitoring of large-span CFST structures, ensuring their long-term structural reliability and construction quality.

AAAI Conference 2026 Conference Paper

QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution

• Bowen Chai
• Zheng Chen
• Libo Zhu
• Wenbo Li
• Yong Guo
• Yulun Zhang

Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment. Quantization offers a potential solution for compressing the VSR model. Nevertheless, quantizing VSR models is challenging due to their temporal characteristics and high fidelity requirements. To address these issues, we propose QuantVSR, a low-bit quantization model for real-world VSR. We propose a spatio-temporal complexity aware (STCA) mechanism, where we first utilize the calibration dataset to measure both spatial and temporal complexities for each layer. Based on these statistics, we allocate layer-specific ranks to the low-rank full-precision (FP) auxiliary branch. Subsequently, we jointly refine the FP and low-bit branches to achieve simultaneous optimization. In addition, we propose a learnable bias alignment (LBA) module to reduce the biased quantization errors. Extensive experiments on synthetic and real-world datasets demonstrate that our method obtains comparable performance with the FP model and significantly outperforms recent leading low-bit quantization methods.

AAAI Conference 2026 Conference Paper

Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

• Zheng Chen
• Mingde Zhou
• Jinpei Guo
• Jiale Yuan
• Yifei Ji
• Yulun Zhang

Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from over-reliance on generative priors. To address these issues, we propose SODEC, a novel single-step diffusion image compression model. We argue that in image compression, a sufficiently informative latent renders multi-step refinement unnecessary. Based on this insight, we leverage a pre-trained VAE-based model to produce latents with rich information, and replace the iterative denoising process with a single-step decoding. Meanwhile, to improve fidelity, we introduce the fidelity guidance module, encouraging output that is faithful to the original image. Furthermore, we design the rate annealing training strategy to enable effective training under extremely low bitrates. Extensive experiments show that SODEC significantly outperforms existing methods, achieving superior rate-distortion-perception performance. Moreover, compared to previous diffusion-based compression models, SODEC improves decoding speed by more than 20×.

AAAI Conference 2026 Conference Paper

Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation

• Rikuto Kotoge
• Ziwei Yang
• Zheng Chen
• Yushun Dong
• Yasuko Matsubara
• Jimeng Sun
• Yasushi Sakurai

Retrieving targeted pathways in biological knowledge bases, particularly when incorporating wet-lab experimental data, remains a challenging task and often requires downstream analyses and specialized expertise. In this paper, we frame this challenge as a solvable graph learning and explaining task and propose a novel subgraph inference framework, ExPath, that explicitly integrates experimental data to classify various graphs (bio-networks) in biological databases. The links (representing pathways) that contribute more to classification can be considered as targeted pathways. Our framework can seamlessly integrate biological foundation models to encode the experimental molecular data. We propose ML-oriented biological evaluations and a new metric. The experiments involving 301 bio-networks evaluations demonstrate that pathways inferred by ExPath are biologically meaningful, achieving up to 4.5× higher Fidelity+ (necessity) and 14× lower Fidelity- (sufficiency) than explainer baselines, while preserving signaling chains up to 4× longer.

EAAI Journal 2025 Journal Article

Benchmarking neural radiance fields for autonomous robots: An overview

• Yuhang Ming
• Xingrui Yang
• Weihan Wang
• Zheng Chen
• Jinglun Feng
• Yifan Xing
• Guofeng Zhang

Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of autonomous robotics, where perception and understanding of the environment are pivotal, NeRF holds immense promise for improving performance. However, few survey has discussed such a potential. To fill this gap, we have collected over 200 papers since the publication of original NeRF in 2020 and present a thorough analysis of how NeRF can be used to enhance the capabilities of autonomous robots. We especially focus on the perception, localization and navigation, and decision-making modules of autonomous robots and delve into tasks crucial for autonomous operation, including 3-dimensional reconstruction, segmentation, pose estimation, simultaneous localization and mapping, navigation and planning, and interaction. Our survey meticulously benchmarks existing NeRF-based methods, comparing their reported performance, and providing insights into their strengths and limitations. Moreover, we target the existing challenges of applying NeRF in autonomous robots, including real-time processing, sparse input views, and explore promising avenues for future research and development in this domain. We especially discuss potential of integrating advanced deep learning techniques like 3-dimensional Gaussian splatting, large language models, and generative artificial intelligence. This survey serves as a roadmap for researchers seeking to leverage NeRF to empower autonomous robots, paving the way for innovative solutions that can navigate and interact seamlessly in complex environments.

AIIM Journal 2025 Journal Article

Developing novel dynamic prediction methods for survival time to analyze short-term and long-term progression of Alzheimer's disease

• Chengfeng Zhang
• Shuyu Chen
• Yanjie Wang
• Pansheng Xue
• Yu Song
• Jiaqiao Ren
• Derun Zhou
• Zheng Chen

Tracking and monitoring mild cognitive impairment (MCI) patients to intervene promptly at the imminent onset of Alzheimer's disease (AD) are crucial. However, existing dynamic survival prediction models for the conversion from MCI to AD are mostly based on hazard rates, which are less intuitive to interpret and require adherence to the proportional hazards assumption. To address this, we propose a Bayesian joint model (JM) based on the time scale indicator of the restricted mean survival time (RMST), which can capture the trajectories of multiple longitudinal covariates and dynamically predict the patient time to event. Using Monte Carlo simulation, it can be demonstrated that the JM method has a better prediction performance compared with the static model. To predict the dynamic progression of AD in MCI patients at different stages, based on the landmark (LM) method and the JM method for RMST, we developed an LM-based model for short-term dynamic prediction (LM-ST model) and a JM-based model for long-term dynamic prediction (JM-LT model) utilizing the ADNI database. The internal and external validation results indicate that the predictive performance of the LM-ST and JM-LT models surpasses that of the static RMST model. Additionally, an online web tool for the two dynamic prediction models was created for clinical application. In summary, we propose a novel method and combined it with the existing LM method for AD progression, which improves the predictive power and provides a scientific basis for medical decision-making.

NeurIPS Conference 2025 Conference Paper

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

• Zheng Chen
• Zichen Zou
• Kewei Zhang
• Xiongfei Su
• Xin Yuan
• Yong Guo
• Yulun Zhang

Diffusion models have demonstrated promising performance in real-world video super-resolution (VSR). However, the dozens of sampling steps they require, make inference extremely slow. Sampling acceleration techniques, particularly single-step, provide a potential solution. Nonetheless, achieving one step in VSR remains challenging, due to the high training overhead on video data and stringent fidelity demands. To tackle the above issues, we propose DOVE, an efficient one-step diffusion model for real-world VSR. DOVE is obtained by fine-tuning a pretrained video diffusion model (*i. e. *, CogVideoX). To effectively train DOVE, we introduce the latent-pixel training strategy. The strategy employs a two-stage scheme to gradually adapt the model to the video super-resolution task. Meanwhile, we design a video processing pipeline to construct a high-quality dataset tailored for VSR, termed HQ-VSR. Fine-tuning on this dataset further enhances the restoration capability of DOVE. Extensive experiments show that DOVE exhibits comparable or superior performance to multi-step diffusion-based VSR methods. It also offers outstanding inference efficiency, achieving up to a **28$\times$** speed-up over existing methods such as MGLD-VSR. Code is available at: https: //github. com/zhengchen1999/DOVE.

AAAI Conference 2025 Conference Paper

Dual-branch Graph Feature Learning for NLOS Imaging

• Xiongfei Su
• Tianyi Zhu
• Lina Liu
• Zheng Chen
• Yulun Zhang
• Siyuan Li
• Juntian Ye
• Feihu Xu

The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems face several significant challenges: (1) The computational and storage requirements are profound due to the inherent three-dimensional grid data structure, which restricts practical application. (2) The simultaneous reconstruction of albedo and depth information requires a delicate balance using hyperparameters in the loss function, rendering the concurrent reconstruction of texture and depth information difficult. This paper introduces the innovative methodology, DG-NLOS, which integrates an albedo-focused reconstruction branch dedicated to albedo information recovery and a depth-focused reconstruction branch that extracts geometrical structure, to overcome these obstacles. The dual-branch framework segregates content delivery to the respective reconstructions, thereby enhancing the quality of the retrieved data. To our knowledge, we are the first to employ the GNN as a fundamental component to transform dense NLOS grid data into sparse structural features for efficient reconstruction. Comprehensive experiments demonstrate that our method attains the highest level of performance among existing methods across synthetic and real data.

NeurIPS Conference 2025 Conference Paper

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks

• Rikuto Kotoge
• Zheng Chen
• Tasuku Kimura
• Yasuko Matsubara
• Takufumi Yanagisawa
• Haruhiko Kishima
• Yasushi Sakurai

Dynamic GNNs, which integrate temporal and spatial features in Electroencephalography (EEG) data, have shown great potential in automating seizure detection. However, fully capturing the underlying dynamics necessary to represent brain states, such as seizure and non-seizure, remains a non-trivial task and presents two fundamental challenges. First, most existing dynamic GNN methods are built on temporally fixed static graphs, which fail to reflect the evolving nature of brain connectivity during seizure progression. Second, current efforts to jointly model temporal signals and graph structures and, more importantly, their interactions remain nascent, often resulting in inconsistent performance. To address these challenges, we present the first theoretical analysis of these two problems, demonstrating the effectiveness and necessity of explicit dynamic modeling and time-then-graph dynamic GNN method. Building on these insights, we propose EvoBrain, a novel seizure detection model that integrates a two-stream Mamba architecture with a GCN enhanced by Laplacian Positional Encoding, following neurological insights. Moreover, EvoBrain incorporates explicitly dynamic graph structures, allowing both nodes and edges to evolve over time. Our contributions include (a) a theoretical analysis proving the expressivity advantage of explicit dynamic modeling and time-then-graph over other approaches, (b) a novel and efficient model that significantly improves AUROC by 23\% and F1 score by 30\%, compared with the dynamic GNN baseline, and (c) broad evaluation of our method on the challenging early seizure prediction task.

NeurIPS Conference 2025 Conference Paper

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

• JUE GONG
• Tingyu Yang
• Jingkai Wang
• Zheng Chen
• Xing Liu
• Hong Gu
• Yulun Zhang
• Xiaokang Yang

Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems often coexist in practice. To address this, we design a degradation pipeline that simulates the coexistence of HMB and generic noise, generating synthetic degraded data to train our proposed HAODiff, a human-aware one-step diffusion. Specifically, we propose a triple-branch dual-prompt guidance (DPG), which leverages high-quality images, residual noise (LQ minus HQ), and HMB segmentation masks as training targets. It produces a positive–negative prompt pair for classifier‑free guidance (CFG) in a single diffusion step. The resulting adaptive dual prompts let HAODiff exploit CFG more effectively, boosting robustness against diverse degradations. For fair evaluation, we introduce MPII‑Test, a benchmark rich in combined noise and HMB cases. Extensive experiments show that our HAODiff surpasses existing state-of-the-art (SOTA) methods in terms of both quantitative metrics and visual quality on synthetic and real-world datasets, including our introduced MPII-Test. Code is available at: https: //github. com/gobunu/HAODiff.

ICRA Conference 2025 Conference Paper

Heuristically Guided Compilation for Task Assignment and Path Finding

• Zheng Chen
• Changlin Chen
• Yiran Ni
• Junhao Wang

We investigate the Combined Target-Assignment and Path-Finding (TAPF) problem that computes both task assignments and collision-free paths for multiple agents, that is, each agent is required to select a target from an underlying set, reaching which leads to a payoff. There is a cost closely related to the time required for each agent to reach the goal. The objective is to maximize the minimum gain generated by the agents. We proposed a Compilation-Based Approach with Heuristics (TA-CBWH) to approximate the optimal solution, behind which are two critical ideas: (i) for a specific task assignment, we formulate an integer linear programming (ILP) and create the iteration combined with large neighborhood search (LNS) to quickly improve the solution quality to near-optimal; (ii) regarding distinct task assignments, a switching mechanism is developed to determine the most promising iteration while progressively eliminating unnecessary task assignments. Comparative experiments demonstrate that TA-CBWH outperforms a wide range of existing approaches across various maps and different numbers of agents.

ICRA Conference 2025 Conference Paper

ICBSS: An Improved Algorithm for Multi-Agent Combinatorial Path Finding

• Zheng Chen
• Changlin Chen
• Yiran Ni

The Multi-Agent Combinatorial Path Finding (MCPF) problem is a generalized version of the Multi-Agent Path Finding (MAPF) problem, in which each agent must collectively visit multiple intermediate target locations on the way to its final destination. The state-of-the-art approach for addressing MCPF, known as Conflict-Based Steiner Search (CBSS) [1], leverages K-best joint sequences to create multiple search trees, and employs a CBS-like search to resolve collisions for each tree. Despite its optimality guarantee, CBSS is computationally burdensome due to the duplicated collision resolutions across multiple trees and the computation of the K best joint sequences. To address these challenges, we propose a novel algorithm called Improved Conflict-Based Steiner Search (ICBSS), aiming at expediting CBSS by replacing the multi trees with a single constraint tree (CT), which can be implemented by interleaving the time-dependent traveling salesman algorithm to compute the optimal joint path for agents under the newly generated constraints in each CT vertex. Additionally, we introduce a sub-optimal variant of ICBSS, which improves computational efficiency at the expense of solution optimality. Empirical results show that ICBSS outperforms state-of-the-art MCPF algorithms on a variety of MAPF instances.

NeurIPS Conference 2025 Conference Paper

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

• Zheng Chen
• Yushi Feng
• Jisheng Dang
• Changyang He
• Yue Deng
• Hongxi Pu
• Haoxuan Li
• Bo Li

Large Language Models (LLMs) have attained human-level fluency in text generation, which complicates the distinguishing between human-written and LLM generated texts. This increases the risk of misuse and highlights the need for reliable detectors. Yet, existing detectors exhibit poor robustness on out-of-distribution (OOD) data and attacked data, which is critical for real-world scenarios. Also, they struggle to provide interpretable evidence to support their decisions, thus undermining reliability. In light of these challenges, we propose IPAD (Inverse Prompt for AI Detection), a novel framework consisting of a Prompt Inverter that identifies predicted prompts that could have generated the input text, and two Distinguishers that examine the probability that the input texts align with the predicted prompts. Empirical evaluations demonstrate that IPAD outperforms the strongest baselines by 9. 05% (Average Recall) on in-distribution data, 12. 93% (AUROC) on out-of-distribution (OOD) data, and 5. 48% (AUROC) on attacked data. IPAD also performs robust on structured datasets. Furthermore, an interpretability assessment is conducted to illustrate that IPAD enhances the AI detection trustworthiness by allowing users to directly examine the decision-making evidence, which provides interpretable support for its state-of-the-art detection results.

AAAI Conference 2025 Conference Paper

Long-Term EEG Partitioning for Seizure Onset Detection

• Zheng Chen
• Yasuko Matsubara
• Yasushi Sakurai
• Jimeng Sun

Deep learning models have recently shown great success in classifying epileptic patients using EEG recordings. Unfortunately, classification-based methods lack a sound mechanism to detect the onset of seizure events. In this work, we propose a two-stage framework, SODor, that explicitly models seizure onset through a novel task formulation of subsequence clustering. Given an EEG sequence, the framework first learns a set of second-level embeddings with label supervision. It then employs model-based clustering to explicitly capture long-term temporal dependencies in EEG sequences and identify meaningful subsequences. Epochs within a subsequence share a common cluster assignment (normal or seizure), with cluster or state transitions representing successful onset detections. Extensive experiments on three datasets demonstrate that our method can correct misclassifications, achieving 5%-11% classification improvements over other baselines and accurately detecting seizure onsets.

NeurIPS Conference 2025 Conference Paper

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

• Jinpei Guo
• Yifei Ji
• Zheng Chen
• Kai Liu
• Min Liu
• Wang Rao
• Wenbo Li
• Yong Guo

Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approaches have achieved high reconstruction quality, their multi-step sampling process incurs substantial computational overhead. Moreover, they typically require training separate models for different compression bit-rates, leading to significant training and storage costs. To address these challenges, we propose a one-step diffusion codec across multiple bit-rates. termed OSCAR. Specifically, our method views compressed latents as noisy variants of the original latents, where the level of distortion depends on the bit-rate. This perspective allows them to be modeled as intermediate states along a diffusion trajectory. By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates. Meanwhile, we argue that the compressed latents retain rich structural information, thereby making one-step denoising feasible. Thus, OSCAR replaces iterative sampling with a single denoising pass, significantly improving inference efficiency. Extensive experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics. The code and models are available at https: //github. com/jp-guo/OSCAR/.

AAAI Conference 2025 Conference Paper

Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing

• Xiongfei Su
• Siyuan Li
• Yuning Cui
• Miao Cao
• Yulun Zhang
• Zheng Chen
• Zongliang Wu
• Zedong Wang

Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real-world applications. In this paper, guided by triple priors, Bright Channel Prior (BCP), Dark Channel Prior (DCP), and Histogram Equalization (HE), we propose a Prior-guided Hierarchical Harmonization Network (PGHHNet) for image dehazing. PGHNet is built upon the UNet-like architecture with an efficient encoder and decoder, consisting of two module types: (1) Prior aggregation module that injects BCP/DCP and selects diverse contexts with gating attention. (2) Feature harmonization modules that subtract low-frequency components from spatial and channel aspects and learn more informative feature distributions to equalize the feature maps. Inspired by observing the sparsity of BCP/DCP and the histogram equalization, we harmonize the deep features using a histogram equation-guided module and further leverage BCP/DCP to guide spatial attention through a sandwich module as the bottleneck. Comprehensive experiments demonstrate that our model efficiently attains the highest level of performance among existing methods across four different datasets for image dehazing tasks.

AAAI Conference 2025 Conference Paper

VFM-Adapter: Adapting Visual Foundation Models for Dense Prediction with Dynamic Hybrid Operation Mapping

• Zheng Chen
• Yu Zeng
• Zehui Chen
• Hongzhi Gao
• Lin Chen
• Jiaming Liu
• Feng Zhao

Although pre-trained large vision foundation models (VFM) yield superior results on various downstream tasks, full fine-tuning is often impractical due to its high computational cost and storage requirements. Recent advancements in parameter-efficient fine-tuning (PEFT) of VFM for image classification show significant promise. However, the application of PEFT techniques to dense prediction tasks remains largely unexplored. Our analysis of existing methods reveals that the underlying premise of utilizing low-rank parameter matrices, despite their efficacy in specific applications, may not be adequately suitable for dense prediction tasks. To this end, we propose a novel PEFT learning approach tailored for dense prediction tasks, namely VFM-Adapter. Specifically, the VFM-Adapter introduces a hybrid operation mapping technique that seamlessly integrates local information with global modeling to the adapter module. It capitalizes on the distinct inductive biases inherent in different operations. Additionally, we dynamically generate parameters for the VFM-Adapter, enabling flexibility of feature extraction given specific inputs. To validate the efficacy of VFM-Adapter, we conduct extensive experiments across object detection, semantic segmentation, and instance segmentation tasks. Results on multiple benchmarks consistently demonstrate the superiority of our method over previous approaches. Notably, with only three percent of the trainable parameters of the SAM-Base backbone, our approach achieves competitive or even superior performance compared to full fine-tuning. The code will be available.

ECAI Conference 2024 Conference Paper

Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities

• Zheyu Zhang 0002
• Xinzhao Liu
• Zheng Chen
• Yueyi Zhang
• Huanjing Yue
• Yunwei Ou
• Xiaoyan Sun 0001

Multi-modal Magnetic Resonance Imaging (MRI) is imperative for accurate brain tumor segmentation, offering indispensable complementary information. Nonetheless, the absence of modalities poses significant challenges in achieving precise segmentation. Recognizing the shared anatomical structures between mono-modal and multi-modal representations, it is noteworthy that mono-modal images typically exhibit limited features in specific regions and tissues. In response to this, we present Anatomical Consistency Distillation and Inconsistency Synthesis (ACDIS), a novel framework designed to transfer anatomical structures from multi-modal to mono-modal representations and synthesize modality-specific features. ACDIS consists of two main components: Anatomical Consistency Distillation (ACD) and Modality Feature Synthesis Block (MFSB). ACD incorporates the Anatomical Feature Enhancement Block (AFEB), meticulously mining anatomical information. Simultaneously, Anatomical Consistency ConsTraints (ACCT) are employed to facilitate the consistent knowledge transfer, i. e. , the richness of information and the similarity in anatomical structure, ensuring precise alignment of structural features across mono-modality and multi-modality. Complementarily, MFSB produces modality-specific features to rectify anatomical inconsistencies, thereby compensating for missing information in the segmented features. Through validation on the BraTS2018 and BraTS2020 datasets, ACDIS substantiates its efficacy in the segmentation of brain tumors with missing MRI modalities.

NeurIPS Conference 2024 Conference Paper

Binarized Diffusion Model for Image Super-Resolution

• Zheng Chen
• Haotong Qin
• Yong Guo
• Xiongfei Su
• Xin Yuan
• Linghe Kong
• Yulun Zhang

Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating DMs. Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation. In this paper, we introduce a novel binarized diffusion model, BI-DiffSR, for image SR. First, for the model structure, we design a UNet architecture optimized for binarization. We propose the consistent-pixel-downsample (CP-Down) and consistent-pixel-upsample (CP-Up) to maintain dimension consistent and facilitate the full-precision information transfer. Meanwhile, we design the channel-shuffle-fusion (CS-Fusion) to enhance feature fusion in skip connection. Second, for the activation difference across timestep, we design the timestep-aware redistribution (TaR) and activation function (TaA). The TaR and TaA dynamically adjust the distribution of activations based on different timesteps, improving the flexibility and representation alability of the binarized module. Comprehensive experiments demonstrate that our BI-DiffSR outperforms existing binarization methods. Code is released at: https: //github. com/zhengchen1999/BI-DiffSR.

NeurIPS Conference 2024 Conference Paper

DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion

• Weicai Ye
• Chenhao Ji
• Zheng Chen
• Junyao Gao
• Xiaoshui Huang
• Song-Hai Zhang
• Wanli Ouyang
• Tong He

Diffusion-based methods have achieved remarkable achievements in 2D image or 3D object generation, however, the generation of 3D scenes and even $360^{\circ}$ images remains constrained, due to the limited number of scene datasets, the complexity of 3D scenes themselves, and the difficulty of generating consistent multi-view images. To address these issues, we first establish a large-scale panoramic video-text dataset containing millions of consecutive panoramic keyframes with corresponding panoramic depths, camera poses, and text descriptions. Then, we propose a novel text-driven panoramic generation framework, termed DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation. Specifically, benefiting from the powerful generative capabilities of stable diffusion, we fine-tune a single-view text-to-panorama diffusion model with LoRA on the established panoramic video-text dataset. We further design a spherical epipolar-aware multi-view diffusion model to ensure the multi-view consistency of the generated panoramic images. Extensive experiments demonstrate that DiffPano can generate scalable, consistent, and diverse panoramic images with given unseen text descriptions and camera poses.

AAMAS Conference 2024 Conference Paper

Fair and Efficient Division of a Discrete Cake with Switching Utility Loss

• Zheng Chen
• Bo Li
• Minming Li
• Guochuan Zhang

Cake cutting is a widely studied model for allocating resources with temporal or spatial structures among agents. Recently, a new line of research has emerged that focuses on the discrete variant, where the resources are indivisible and connected by a path. In some real-world applications, the resources are interdependent, and dividing the cake may reduce their effectiveness. In this paper, we introduce a model that captures the effect of division as switching utility loss and investigate the tradeoff between fairness and efficiency for various settings. Specifically, we measure fairness and efficiency using the popular notions of envy-freeness up to one item (EF1) and social welfare, respectively. The goal of our study is to understand how much social welfare must be sacrificed to ensure EF1 allocations and design polynomial-time algorithms that can compute EF1 allocations with the best possible social welfare guarantee.

AAAI Conference 2024 Conference Paper

Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection

• Hongzhi Gao
• Zheng Chen
• Zehui Chen
• Lin Chen
• Jiaming Liu
• Shanghang Zhang
• Feng Zhao

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for practical applications in 3D detection, which is not only more accessible and less expensive but also provides strong spatial information for object localization. In this paper, we empirically discover that it is non-trivial to merely adapt Point-DETR to its 3D form, encountering two main bottlenecks: 1) it fails to encode strong 3D prior into the model, and 2) it generates low-quality pseudo labels in distant regions due to the extreme sparsity of LiDAR points. To overcome these challenges, we introduce Point-DETR3D, a teacher-student framework for weakly semi-supervised 3D detection, designed to fully capitalize on point-wise supervision within a constrained instance-wise annotation budget. Different from Point-DETR which encodes 3D positional information solely through a point encoder, we propose an explicit positional query initialization strategy to enhance the positional prior. Considering the low quality of pseudo labels at distant regions produced by the teacher model, we enhance the detector's perception by incorporating dense imagery data through a novel Cross-Modal Deformable RoI Fusion (D-RoI). Moreover, an innovative point-guided self-supervised learning technique is proposed to allow for fully exploiting point priors, even in student models. Extensive experiments on representative nuScenes dataset demonstrate our Point-DETR3D obtains significant improvements compared to previous works. Notably, with only 5% of labeled data, Point-DETR3D achieves over 90% performance of its fully supervised counterpart.

JBHI Journal 2023 Journal Article

A Dynamic Prediction Model Supporting Individual Life Expectancy Prediction Based on Longitudinal Time-Dependent Covariates

• Chengfeng Zhang
• Zhaojin LI
• Zijing Yang
• Baoyi Huang
• Yawen Hou
• Zheng Chen

In the field of clinical chronic diseases, common prediction results (such as survival rate) and effect size hazard ratio (HR) are relative indicators, resulting in more abstract information. However, clinicians and patients are more interested in simple and intuitive concepts of (survival) time, such as how long a patient may live or how much longer a patient in a treatment group will live. In addition, due to the long follow-up time, resulting in generation of longitudinal time-dependent covariate information, patients are interested in how long they will survive at each follow-up visit. In this study, based on a time scale indicator—restricted mean survival time (RMST)—we proposed a dynamic RMST prediction model by considering longitudinal time-dependent covariates and utilizing joint model techniques. The model can describe the change trajectory of longitudinal time-dependent covariates and predict the average survival times of patients at different time points (such as follow-up visits). Simulation studies through Monte Carlo cross-validation showed that the dynamic RMST prediction model was superior to the static RMST model. In addition, the dynamic RMST prediction model was applied to a primary biliary cirrhosis (PBC) population to dynamically predict the average survival times of the patients, and the average C-index of the internal validation of the model reached 0. 81, which was better than that of the static RMST regression. Therefore, the proposed dynamic RMST prediction model has better performance in prediction and can provide a scientific basis for clinicians and patients to make clinical decisions.

NeurIPS Conference 2023 Conference Paper

General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence

• Lingwei Zhu
• Zheng Chen
• Matthew Schlegel
• Martha White

Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on Conservative Policy Iteration, with approximations given by algorithms like TRPO and Munchausen Value Iteration (MVI). We continue this line of work by investigating a generalized KL divergence---called the Tsallis KL divergence. Tsallis KL defined by the $q$-logarithm is a strict generalization, as $q = 1$ corresponds to the standard KL divergence; $q > 1$ provides a range of new options. We characterize the types of policies learned under the Tsallis KL, and motivate when $q >1$ could be beneficial. To obtain a practical algorithm that incorporates Tsallis KL regularization, we extend MVI, which is one of the simplest approaches to incorporate KL regularization. We show that this generalized MVI($q$) obtains significant improvements over the standard MVI($q = 1$) across 35 Atari games.

NeurIPS Conference 2023 Conference Paper

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

• Zheng Chen
• Yulun Zhang
• Ding Liu
• Bin Xia
• Jinjin Gu
• Linghe Kong
• Xin Yuan

Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to recover the clean image from pure Gaussian noise, which consumes massive computational resources. Moreover, the distribution synthesized by the diffusion model is often misaligned with the target results, leading to restrictions in distortion-based metrics. To address the above issues, we propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process. The deblurring process is implemented by a regression-based method to obtain better distortion accuracy. Meanwhile, the highly compact latent space ensures the efficiency of the DM. Furthermore, we design the hierarchical integration module to fuse the prior into the regression-based model from multiple scales, enabling better generalization in complex blurry scenarios. Comprehensive experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods. Code and trained models are available at https: //github. com/zhengchen1999/HI-Diff.

NeurIPS Conference 2023 Conference Paper

Learning to Tokenize for Generative Retrieval

• Weiwei Sun
• Lingyong Yan
• Zheng Chen
• Shuaiqiang Wang
• Haichao Zhu
• Pengjie Ren
• Zhumin Chen
• Dawei Yin

As a new paradigm in information retrieval, generative retrieval directly generates a ranked list of document identifiers (docids) for a given query using generative language models (LMs). How to assign each document a unique docid (denoted as document tokenization) is a critical problem, because it determines whether the generative retrieval model can precisely retrieve any document by simply decoding its docid. Most existing methods adopt rule-based tokenization, which is ad-hoc and does not generalize well. In contrast, in this paper we propose a novel document tokenization learning method, GenRet, which learns to encode the complete document semantics into docids. GenRet learns to tokenize documents into short discrete representations (i. e. , docids) via a discrete auto-encoding approach. We develop a progressive training scheme to capture the autoregressive nature of docids and diverse clustering techniques to stabilize the training process. Based on the semantic-embedded docids of any set of documents, the generative retrieval model can learn to generate the most relevant docid only according to the docids' semantic relevance to the queries. We conduct experiments on the NQ320K, MS MARCO, and BEIR datasets. GenRet establishes the new state-of-the-art on the NQ320K dataset. Compared to generative retrieval baselines, GenRet can achieve significant improvements on unseen documents. Moreover, GenRet can also outperform comparable baselines on MS MARCO and BEIR, demonstrating the method's generalizability.

NeurIPS Conference 2023 Conference Paper

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

• Zheng Chen
• Yan-Pei Cao
• Yuan-Chen Guo
• Chen Wang
• Ying Shan
• Song-Hai Zhang

Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these applications to reduce network bandwidth and storage requirements. However, synthesizing novel views from these panoramas remains a key challenge. Although existing neural radiance field methods can produce photorealistic views under narrow-baseline and dense image captures, they tend to overfit the training views when dealing with wide-baseline panoramas due to the difficulty in learning accurate geometry from sparse $360^{\circ}$ views. To address this problem, we propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas, which construct spherical radiance fields incorporating $360^{\circ}$ scene priors. Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion and directly aggregates geometry and appearance features of 3D sample points from each panoramic view based on spherical projection. Moreover, as some regions of the panorama are only visible from one view while invisible from others under wide baseline settings, PanoGRF incorporates $360^{\circ}$ monocular depth priors into spherical depth estimation to improve the geometry features. Experimental results on multiple panoramic datasets demonstrate that PanoGRF significantly outperforms state-of-the-art generalizable view synthesis methods for wide-baseline panoramas (e. g. , OmniSyn) and perspective images (e. g. , IBRNet, NeuRay).

NeurIPS Conference 2022 Conference Paper

Cross Aggregation Transformer for Image Restoration

• Zheng Chen
• Yulun Zhang
• Jinjin Gu
• Yongbing Zhang
• Linghe Kong
• Xin Yuan

Recently, Transformer architecture has been introduced into image restoration to replace convolution neural network (CNN) with surprising results. Considering the high computational complexity of Transformer with global attention, some methods use the local square window to limit the scope of self-attention. However, these methods lack direct interaction among different windows, which limits the establishment of long-range dependencies. To address the above issue, we propose a new image restoration model, Cross Aggregation Transformer (CAT). The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the features cross different windows. We also introduce the Axial-Shift operation for different window interactions. Furthermore, we propose the Locality Complementary Module to complement the self-attention mechanism, which incorporates the inductive bias of CNN (e. g. , translation invariance and locality) into Transformer, enabling global-local coupling. Extensive experiments demonstrate that our CAT outperforms recent state-of-the-art methods on several image restoration applications. The code and models are available at https: //github. com/zhengchen1999/CAT.

IJCAI Conference 2022 Conference Paper

Multi-Tier Platform for Cognizing Massive Electroencephalogram

• Zheng Chen
• Lingwei Zhu
• Ziwei Yang
• Renyuan Zhang

An end-to-end platform assembling multiple tiers is built for precisely cognizing brain activities. Being fed massive electroencephalogram (EEG) data, the time-frequency spectrograms are conventionally projected into the episode-wise feature matrices (seen as tier-1). A spiking neural network (SNN) based tier is designed to distill the principle information in terms of spike-streams from the rare features, which maintains the temporal implication in the nature of EEGs. The proposed tier-3 transposes time- and space-domain of spike patterns from the SNN; and feeds the transposed pattern-matrices into an artificial neural network (ANN, Transformer specifically) known as tier-4, where a special spanning topology is proposed to match the two-dimensional input form. In this manner, cognition such as classification is conducted with high accuracy. For proof-of-concept, the sleep stage scoring problem is demonstrated by introducing multiple EEG datasets with the largest comprising 42, 560 hours recorded from 5, 793 subjects. From experiment results, our platform achieves the general cognition overall accuracy of 87% by leveraging sole EEG, which is 2% superior to the state-of-the-art. Moreover, our developed multi-tier methodology offers visible and graphical interpretations of the temporal characteristics of EEG by identifying the critical episodes, which is demanded in neurodynamics but hardly appears in conventional cognition scenarios.

TCS Journal 2021 Journal Article

Which is the fairest allocation in the max-min fairness-based coalitional game?

• Zheng Chen
• Zhaoquan Gu
• Yuexuan Wang

In the coalitional game, the agents (nodes) cooperate or compete with each other to maximize their own benefits, thereby creating different coalitions. Designing a fair resource-allocation mechanism can reduce conflicts among agents and enable an all-win scenario. One popular resource-exchange mechanism, the max-min fairness-based coalitional (MMFC) mechanism, achieves fair allocation of resource by finding the max-min resource-exchange rate in a resource exchange network. However, this mechanism cannot ensure envy-free allocation of resource among the agents. To solve this problem, we proposed an envy-free resource-allocation mechanism called the envy-free max-min fairness-based coalitional (EFMMFC) mechanism, in which the resource-exchange rates of all agents constitute a max-min fair vector. EFMMFC mechanism opens new research directions in developing simple and efficient protocol that can produce envy-free allocation subject to the max-min resource exchange rate in coalitional game.

AAAI Conference 2015 Conference Paper

Marginalized Denoising for Link Prediction and Multi-Label Learning

• Zheng Chen
• Minmin Chen
• Kilian Weinberger
• Weixiong Zhang

Link prediction and multi-label learning on graphs are two important but challenging machine learning problems that have broad applications in diverse fields. Not only are the two problems inherently correlated and often appear concurrently, they are also exacerbated by incomplete data. We develop a novel algorithm to solve these two problems jointly under a unified framework, which helps reduce the impact of graph noise and benefits both tasks individually. We reduce multilabel learning problem into an additional link prediction task and solve both problems with marginalized denoising, which we co-regularize with Laplacian smoothing. This approach combines both learning tasks into a single convex objective function, which we optimize efficiently with iterative closedform updates. The resulting approach performs significantly better than prior work on several important real-world applications with great consistency.

AAAI Conference 2015 Conference Paper

Maximin Separation Probability Clustering

• Gao Huang
• Jianwen Zhang
• Shiji Song
• Zheng Chen

This paper proposes a new approach for discriminative clustering. The intuition is, for a good clustering, one should be able to learn a classifier from the clustering labels with high generalization accuracy. Thus we define a novel metric to evaluate the quality of a clustering labeling, named Minimum Separation Probability (MSP), which is a lower bound of the generalization accuracy of a classifier learnt from the clustering labeling. We take MSP as the objective to maximize and propose our approach Maximin Separation Probability Clustering (MSPC), which has several attractive properties, such as invariance to anisotropic feature scaling and intuitive probabilistic explanation for clustering quality. We present three efficient optimization strategies for MSPC, and analyze their interesting connections to existing clustering approaches, such as maximum margin clustering (MMC) and discriminative k-means. Empirical results on real world data sets verify that MSP is a robust and effective clustering quality measure. It is also shown that the proposed algorithms compare favorably to state-of-the-art clustering algorithms in both accuracy and efficiency.

AAAI Conference 2015 Conference Paper

Modeling with Node Degree Preservation Can Accurately Find Communities

• Di Jin
• Zheng Chen
• Dongxiao He
• Weixiong Zhang

An important problem in analyzing complex networks is discovery of modular or community structures embedded in the networks. Although being promising for identifying network communities, the popular stochastic models often do not preserve node degrees, thus reducing their representation power and applicability to real-world networks. Here we address this critical problem. Instead of using a blockmodel, we adopted a random-graph null model to faithfully capture community structures by preserving in the model the expected node degrees. The new model, learned using nonnegative matrix factorization, is more accurate and robust in representing community structures than the existing methods. Our results from extensive experiments on synthetic benchmarks and real-world networks show the superior performance of the new method over the existing methods in detecting both disjoint and overlapping communities.

AAAI Conference 2014 Conference Paper

Knowledge Graph Embedding by Translating on Hyperplanes

• Zhen Wang
• Jianwen Zhang
• Jianlin Feng
• Zheng Chen

We deal with embedding a large scale knowledge graph composed of entities and relations into a continuous vector space. TransE is a promising method proposed recently, which is very efficient while achieving state-of-the-art predictive performance. We discuss some mapping properties of relations which should be considered in embedding, such as reflexive, one-to-many, many-to-one, and many-to-many. We note that TransE does not do well in dealing with these properties. Some complex models are capable of preserving these mapping properties but sacrifice efficiency in the process. To make a good trade-off between model capacity and efficiency, in this paper we propose TransH which models a relation as a hyperplane together with a translation operation on it. In this way, we can well preserve the above mapping properties of relations with almost the same model complexity of TransE. Additionally, as a practical knowledge graph is often far from completed, how to construct negative examples to reduce false negative labels in training is very important. Utilizing the one-to-many/many-to-one mapping property of a relation, we propose a simple trick to reduce the possibility of false negative labeling. We conduct extensive experiments on link prediction, triplet classification and fact extraction on benchmark datasets like WordNet and Freebase. Experiments show TransH delivers significant improvements over TransE on predictive accuracy with comparable capability to scale up.

AAAI Conference 2014 Conference Paper

Pre-Trained Multi-View Word Embedding Using Two-Side Neural Network

• Yong Luo
• Jian Tang
• Jun Yan
• Chao Xu
• Zheng Chen

Word embedding aims to learn a continuous representation for each word. It attracts increasing attention due to its effectiveness in various tasks such as named entity recognition and language modeling. Most existing word embedding results are generally trained on one individual data source such as news pages or Wikipedia articles. However, when we apply them to other tasks such as web search, the performance suffers. To obtain a robust word embedding for different applications, multiple data sources could be leveraged. In this paper, we proposed a two-side multimodal neural network to learn a robust word embedding from multiple data sources including free text, user search queries and search click-through data. This framework takes the word embeddings learned from different data sources as pre-train, and then uses a two-side neural network to unify these embeddings. The pre-trained embeddings are obtained by adapting the recently proposed CBOW algorithm. Since the proposed neural network does not need to re-train word embeddings for a new task, it is highly scalable in real world problem solving. Besides, the network allows weighting different sources differently when applied to different application tasks. Experiments on two real-world applications including web search ranking and word similarity measuring show that our neural network with multiple sources outperforms state-of-the-art word embedding algorithm with each individual source. It also outperforms other competitive baselines using multiple sources.

AAAI Conference 2013 Conference Paper

A Hierarchical Aspect-Sentiment Model for Online Reviews

• Suin Kim
• Jianwen Zhang
• Zheng Chen
• Alice Oh
• Shixia Liu

To help users quickly understand the major opinions from massive online reviews, it is important to automatically reveal the latent structure of the aspects, sentiment polarities, and the association between them. However, there is little work available to do this effectively. In this paper, we propose a hierarchical aspect sentiment model (HASM) to discover a hierarchical structure of aspect-based sentiments from unlabeled online reviews. In HASM, the whole structure is a tree. Each node itself is a two-level tree, whose root represents an aspect and the children represent the sentiment polarities associated with it. Each aspect or sentiment polarity is modeled as a distribution of words. To automatically extract both the structure and parameters of the tree, we use a Bayesian nonparametric model, recursive Chinese Restaurant Process (rCRP), as the prior and jointly infer the aspect-sentiment tree from the review texts. Experiments on two real datasets show that our model is comparable to two other hierarchical topic models in terms of quantitative measures of topic trees. It is also shown that our model achieves better sentence-level classification accuracy than previously proposed aspect-sentiment joint models.

IJCAI Conference 2013 Conference Paper

Domain Adaptation with Topical Correspondence Learning

• Zheng Chen
• Weixiong Zhang

A serious and ubiquitous issue in machine learning is the lack of sufficient training data in a domain of interest. Domain adaptation is an effective approach to dealing with this problem by transferring information or models learned from related, albeit distinct, domains to the target domain. We develop a novel domain adaptation method for text document classification under the framework of Nonnegative Matrix Factorization. Two key ideas of our method are to construct a latent topic space where a topic is decomposed into common words shared by all domains and words specific to individual domains, and then to establish associations between words in different domains through the common words as a bridge for knowledge transfer. The correspondence between cross-domain topics leads to more coherent distributions of source and target domains in the new representation while preserving the predictive power. Our new method outperformed several state-of-the-art domain adaptation methods on several benchmark datasets.

ICRA Conference 2011 Conference Paper

A novel electroactive polymer buoyancy control device for bio-inspired underwater vehicles

• Tae I. Um
• Zheng Chen
• Hilary Bart-Smith

A novel depth control device has been designed and built. The proof-of-concept device utilizes the principles of electrolysis of water, enhanced by the inclusion of an ionic polymer-metal composite (IPMC) membrane as a medium. The device design incorporates an artificial bladder where the volume of gas generated by electrolysis is controlled by a solenoid valve, thus changing the device's buoyancy. A set of gold electrodes, separated by an IPMC film, is used as a lightweight and compact electrolysis generator. IPMC acts as stable, low power, highly efficient and environmentally friendly gas generator. Experimental results using open-loop control show that the device is capable of controlling its buoyancy efficiently with no noise and low power consumption. Applications for this technology include integration into bio-inspired, unmanned underwater vehicles.

AAAI Conference 2011 Conference Paper

Collaborative Users’ Brand Preference Mining across Multiple Domains from Implicit Feedbacks

• Jian Tang
• Jun Yan
• Lei Ji
• Ming Zhang
• Shaodan Guo
• Ning Liu
• Xianfang Wang
• Zheng Chen

Advanced e-applications require comprehensive knowledge about their users’ preferences in order to provide accurate personalized services. In this paper, we propose to learn users’ preferences to product brands from their implicit feedbacks such as their searching and browsing behaviors in user Web browsing log data. The user brand preference learning problem is challenge since (1) the users’ implicit feedbacks are extremely sparse in various product domains; and (2) we can only observe positive feedbacks from users’ behaviors. In this paper, we propose a latent factor model to collaboratively mine users’ brand preferences across multiple domains simultaneously. By collective learning, the learning processes in all the domains are mutually enhanced and hence the problem of data scarcity in each single domain can be effectively addressed. On the other hand, we learn our model with an adaption of the Bayesian personalized ranking (BPR) optimization criterion which is a general learning framework for collaborative filtering from implicit feedbacks. Experiments with both synthetic and real world datasets show that our proposed model significantly outperforms the baselines.

IROS Conference 2009 Conference Paper

Analytical and computational modeling of robotic fish propelled by soft actuation material-based active joints

• Mart Anton
• Zheng Chen
• Maarja Kruusmaa
• Xiaobo Tan 0001

Soft actuation materials, such as Ionic Polymer-Metal Composites (IPMCs), are gaining increasing interest in robotic applications since they lead to compact and biomimetic designs. In this paper, we propose the use of soft actuation materials as active joints for propelling biomimetic robotic fish. An analytical model is developed to compute the thrust force generated by a two-link tail and the resulting moments in the active joints. The computed joint moments can be combined with internal dynamics of actuation materials to provide realistic kinematic constraints for the joints. Computational fluid dynamics (CFD) modeling is also adopted to examine the flow field, the produced thrust, and the bending moments in joints for the two-link tail. Good agreement is achieved between the analytical modeling and the CFD modeling, which points to a promising two-tier framework for the understanding and optimization of robotic fish with a multi-link tail. We also show that, comparing to a one-link bending tail, a two-link tail is able to produce much higher thrust and more versatile maneuvers, such as backward swimming.

AAAI Conference 2008 Conference Paper

Mining Translations of Web Queries from Web Click-through Data

• Rong Hu
• Jian Hu
• Zheng Chen

Query translation for Cross-Lingual Information Retrieval (CLIR) has gained increasing attention in the research area. Previous work mainly used machine translation systems, bilingual dictionaries, or web corpora to perform query translation. However, most of these approaches require either expensive language resources or complex language models, and cannot achieve timely translation for new queries. In this paper, we propose a novel solution to automatically acquire query translation pairs from the knowledge hidden in the click-through data, that are represented by the URL a user clicks after submitting a query to a search engine. Our proposed solution consists of two stages: identifying bilingual URL pair patterns in the click-through data and matching query translation pairs based on user click behavior. Experimental results on a real dataset show that our method not only generates existing query translation pairs with high precision, but also generates many timely query translation pairs that could not be obtained by previous methods. A comparative study between our system and two commercial online translation systems shows the advantage of our proposed method.

ICRA Conference 2008 Conference Paper

Modeling of biomimetic robotic fish propelled by an ionic polymer-metal composite actuator

• Ernest Mbemmo
• Zheng Chen
• Stephan Shatara
• Xiaobo Tan 0001

In this paper a physics-based model is proposed for a biomimetic robotic fish propelled by an ionic polymermetal composite (IPMC) actuator. Inspired by biological fins, a passive plastic foil is attached to the IPMC beam. The model incorporates both IPMC actuation dynamics and the hydrodynamics, and captures the interactions between the IPMC actuator and the plastic foil. Experimental results have shown that the proposed model is able to predict the steady-state cruising speed of the robotic fish under a periodic actuation input. Since the majority of the model parameters are expressed in terms of fundamental physical properties and geometric dimensions, the model is expected to be instrumental in optimal design of the robotic fish.

IJCAI Conference 2007 Conference Paper

• Bin Cao
• Dou Shen
• Jian-Tao Sun
• Xuanhui Wang
• Qiang Yang
• Zheng Chen

Detecting and tracking latent factors from temporal data is an important task. Most existing algorithms for latent topic detection such as Nonnegative Matrix Factorization (NMF) have been designed for static data. These algorithms are unable to capture the dynamic nature of temporally changing data streams. In this paper, we put forward an online NMF (ONMF) algorithm to detect latent factors and track their evolution while the data evolve. By leveraging the already detected latent factors and the newly arriving data, the latent factors are automatically and incrementally updated to reflect the change of factors. Furthermore, by imposing orthogonality on the detected latent factors, we can not only guarantee the unique solution of NMF but also alleviate the partial-data problem, which may cause NMF to fail when the data are scarce or the distribution is incomplete. Experiments on both synthesized data and real data validate the efficiency and effectiveness of our ONMF algorithm.

IJCAI Conference 2007 Conference Paper

• Dou Shen
• Jian-Tao Sun
• Hua Li
• Qiang Yang
• Zheng Chen

Many methods, including supervised and unsupervised algorithms, have been developed for extractive document summarization. Most supervised methods consider the summarization task as a two-class classification problem and classify each sentence individually without leveraging the relationship among sentences. The unsupervised methods use heuristic rules to select the most informative sentences into a summary directly, which are hard to generalize. In this paper, we present a Conditional Random Fields (CRF) based framework to keep the merits of the above two kinds of approaches while avoiding their disadvantages. What is more, the proposed framework can take the outcomes of previous methods as features and seamlessly integrate them. The key idea of our approach is to treat the summarization task as a sequence labeling problem. In this view, each document is a sequence of sentences and the summarization procedure labels the sentences by 1 and 0. The label of a sentence depends on the assignment of labels of others. We compared our proposed approach with eight existing methods on an open benchmark data set. The results show that our approach can improve the performance by more than 7. 1% and 12. 1% over the best supervised baseline and unsupervised baseline respectively in terms of two popular metrics F1 and ROUGE-2. Detailed analysis of the improvement is presented as well.