Bin Zhang

JBHI Journal 2026 Journal Article

Asymmetric Co-Training With Decoder–Head Decoupling for Semi-Supervised Medical Image Segmentation

• Yuxin Tian
• Muhan Shi
• Jianxun Li
• Bin Zhang
• Min Qu
• Yinxue Shi
• Xian Yang
• Min Wang

Semi-supervised learning reduces annotation costs in medical image segmentation by leveraging abundant unlabeled data alongside scarce labels. Most models adopt an encoder–decoder architecture with a task-specific segmentation head. While co-training is effective, existing frameworks suffer from intra-network coupling (decoder–head binding) and inter-network coupling (over-aligned predictions), which reduce prediction diversity and amplify confirmation bias–particularly for small structures, ambiguous boundaries, and anatomically variable regions. We propose AsyCo, an asymmetric co-training framework with two components. (1) Asymmetric Decoder Coupling implements decoder–head decoupling by dynamically remapping encoder–decoder features to non-default heads across branches, breaking intra-network coupling and creating diverse prediction paths without additional parameters. (2) Hierarchical Consistency Regularization converts this diversity into stable supervision by aligning (i) the two branches' final outputs along their default paths (branch-output consistency), (ii) predictions from different segmentation heads evaluated on identical decoder features (inter-head consistency), and (iii) intermediate encoder–decoder representations (representation consistency). Through these mechanisms, AsyCo explicitly mitigates both intra- and inter-network coupling, improving training stability and reducing confirmation bias. Extensive experiments on three clinical benchmarks under limited-label regimes demonstrate that AsyCo consistently outperforms nine state-of-the-art semi-supervised learning methods. These results indicate that AsyCo delivers accurate and reliable segmentation with minimal annotation, thereby enhancing the reliability of medical image analysis in real-world clinical practice.

EAAI Journal 2026 Journal Article

Global-local contrastive learning: A multi-operating-condition guided approach for few-shot cross-domain bearing fault diagnosis

• Yue Zhang
• Xinye Chen
• Jie Lai
• Bin Zhang
• Zhuyun Chen
• Fei Jiang

Although existing transfer learning approaches have demonstrated their potential in cross-domain bearing fault diagnosis, they predominantly rely on single-source operating conditions and emphasize global feature alignment between domains. This single-domain paradigm introduces two critical limitations: insufficient adaptation of decision boundaries for target domain distributions, and neglect of discriminative local features across varying operational conditions. To overcome these challenges, a multi-operating-condition-guided approach with global-local contrastive learning for few-shot cross-domain fault diagnosis is proposed. Our methodology innovatively integrates multi-source domain supervision with contrastive feature learning through two key mechanisms: global contrastive alignment, which preserves condition-invariant characteristics across multiple operational domains, and local contrastive refinement, which enhances discriminative feature learning through fine-grained sample relationships. By jointly optimizing global and local contrastive objectives, the proposed method effectively bridges domain discrepancies while maintaining condition-specific discriminability, particularly in few-shot scenarios in which only limited labeled target samples are available. Comprehensive evaluations of two rotating machinery datasets demonstrated that the proposed method achieved superior cross-domain diagnostic accuracy and enhanced stability compared with other popular transfer learning methods. https: //github. com/xinyeC/fircode1024cc/tree/main/GLCL.

AAAI Conference 2026 Conference Paper

Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs

• Jiwei Fang
• Bin Zhang
• Changwei Wang
• Jin Wan
• Zhiwei Xu

Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often rigid. They struggle to adapt to diverse reasoning structures, from formal proofs to informal natural language narratives. To address this adaptability gap, we propose the Graph of Verification (GoV), a novel framework for adaptable and multi-granular verification. GoV's core innovation is its flexible node block architecture. This mechanism allows GoV to adaptively adjust its verification granularity—from atomic steps for formal tasks to entire paragraphs for natural language—to match the native structure of the reasoning process. This flexibility allows GoV to resolve the fundamental trade-off between verification precision and robustness. Experiments on both well-structured and loosely-structured benchmarks demonstrate GoV's versatility. The results show that GoV's adaptive approach significantly outperforms both holistic baselines and other state-of-the-art decomposition-based methods, establishing a new standard for training-free reasoning verification.

AAAI Conference 2026 Conference Paper

Monocular Mesh Recovery and Body Measurement of Female Saanen Goats

• Bo Jin
• ShichaoZhao
• Jin Lyu
• Bin Zhang
• Tao Yu
• Liang An
• Yebin Liu
• Meili Wang

The lactation performance of Saanen dairy goats, renowned for their high milk yield, is intrinsically linked to their body size, making accurate 3D body measurement essential for assessing milk production potential, yet existing reconstruction methods lack goat-specific authentic 3D data. To address this limitation, we establish the FemaleSaanenGoat dataset containing synchronized eight-view RGBD videos of 55 female Saanen goats (6-18 months). Using multi-view DynamicFusion, we fuse noisy, non-rigid point cloud sequences into high-fidelity 3D scans, overcoming challenges from irregular surfaces and rapid movement. Based on these scans, we develop SaanenGoat, a parametric 3D shape model specifically designed for female Saanen goats. This model features a refined template with 41 skeletal joints and enhanced udder representation, registered with our scan data. A comprehensive shape space constructed from 48 goats enables precise representation of diverse individual variations. With the help of SaanenGoat model, we get high-precision 3D reconstruction from single-view RGBD input, and achieve automated measurement of six critical body dimensions: body length, height, chest width, chest girth, hip width, and hip height. Experimental results demonstrate the superior accuracy of our method in both 3D reconstruction and body measurement, presenting a novel paradigm for large-scale 3D vision applications in precision livestock farming.

AAMAS Conference 2026 Conference Paper

Quality-Diversity for Multi-Agent Reinforcement Learning

• Hao Chen
• Pengyi Li
• Bin Zhang
• Hu Fu
• Zhiwei Xu
• Ce Zhang
• Xinyue Lu
• Guoliang Fan

Quality–diversity optimization (QD) in multi-agent reinforcement learning (MARL) aims to evolve a population of team policies that are both high-performing and behaviorally diverse, enabling effective coordination in complex cooperative tasks. However, existing QD approaches often depend on random exploration to encourage diversity, resulting in unstable learning and limited coverage in high-dimensional environments. We propose MIQD, a mutualinformation–enhanced QD framework that integrates fragmentbased behavioral descriptors into the critic to capture short-term patterns and guide policy updates. Mutual information measures alignment between policy behavior and target descriptors; its steplevel decomposition yields intrinsic rewards that promote alignment at each state–action pair. Experimental results show that our method consistently outperforms strong baselines across multiple metrics, demonstrating its effectiveness in jointly enhancing policy quality and diversity.

AAAI Conference 2026 Conference Paper

SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-Compute

• Bowen Shen
• Yuyue Chen
• Peng Yang
• Bin Zhang
• Xi Zhang
• Zoe L. Jiang

Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A possible way to close this gap is the Mixture of Experts (MoE) architecture, which has emerged as a promising technique to scale up model capacity with minimal overhead. However, given that the current secure two-party (2-PC) protocols allow the server to homomorphically compute the FFN layer with its plaintext model weight, under the MoE setting, this could reveal which expert is activated to the server, exposing token-level privacy about the client's input. While naively evaluating all the experts before selection could protect privacy, it nullifies MoE sparsity and incurs the heavy computational overhead that sparse MoE seeks to avoid. To address the privacy and efficiency limitations above, we propose a 2-PC privacy-preserving inference framework, SecMoE. Unifying per-entry circuits in both the MoE layer and piecewise polynomial functions, SecMoE obliviously selects the extracted parameters from circuits and only computes one encrypted entry, which we refer to as Select-Then-Compute. This makes the model for private inference scale to 63× larger while only having a 15.2× increase in end-to-end runtime. Extensive experiments show that, under 5 expert settings, SecMoE lowers the end-to-end private inference communication by 1.8~7.1× and achieves 1.3~3.8× speedup compared to the state-of-the-art (SOTA) protocols.

AAAI Conference 2026 Conference Paper

SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images

• Xuejun Huang
• Xinyi Liu
• Yi Wan
• Zhi Zheng
• Bin Zhang
• Mingtao Xiong
• Yingying Pei
• Yongjun Zhang

Three-dimensional scene reconstruction from sparse-view satellite images is a long-standing and challenging task. While 3D Gaussian Splatting (3DGS) and its variants have recently attracted attention for its high efficiency, existing methods remain unsuitable for satellite images due to incompatibility with rational polynomial coefficient (RPC) models and limited generalization capability. Recent advances in generalizable 3DGS approaches show potential, but they perform poorly on multi-temporal sparse satellite images due to limited geometric constraints, transient objects, and radiometric inconsistencies. To address these limitations, we propose SkySplat, a novel self-supervised framework that integrates the RPC model into the generalizable 3DGS pipeline, enabling more effective use of sparse geometric cues for improved reconstruction. SkySplat relies only on RGB images and radiometric-robust relative height supervision, thereby eliminating the need for ground-truth height maps. Key components include a Cross-Self Consistency Module (CSCM), which mitigates transient object interference via consistency-based masking, and a multi-view consistency aggregation strategy that refines reconstruction results. Compared to per-scene optimization methods, SkySplat achieves an 86 times speedup over EOGS with higher accuracy. It also outperforms generalizable 3DGS baselines, reducing MAE from 13.18 m to 1.80 m on the DFC19 dataset significantly, and demonstrates strong cross-dataset generalization on the MVS3D benchmark.

ICRA Conference 2025 Conference Paper

A Refined 3D Gaussian Representation for High-Quality Dynamic Scene Reconstruction

• Bin Zhang
• Bi Zeng
• Zexin Peng

In recent years, Neural Radiance Fields (NeRF) has revolutionized three-dimensional (3D) reconstruction with its implicit representation. Building upon NeRF, 3D Gaussian Splatting (3D-GS) has departed from the implicit representation of neural networks and instead directly represents scenes as point clouds with Gaussian-shaped distributions. While this shift has notably elevated the rendering quality and speed of radiance fields but inevitably led to a significant increase in memory usage. Additionally, effectively rendering dynamic scenes in 3D-GS has emerged as a pressing challenge. To address these concerns, this paper proposes a refined 3D Gaussian representation for high-quality dynamic scene reconstruction. Firstly, we use a deformable multi-layer perceptron (MLP) network to capture the dynamic offset of Gaussian points and express the color features of points through hash encoding and a tiny MLP to reduce storage requirements. Subsequently, we introduce a learnable denoising mask coupled with denoising loss to eliminate noise points from the scene, thereby further compressing 3D Gaussian model. Finally, motion noise of points is mitigated through static constraints and motion consistency constraints. Experimental results demonstrate that our method surpasses existing approaches in rendering quality and speed, while significantly reducing the memory usage associated with 3D-GS, making it highly suitable for various tasks such as novel view synthesis, and dynamic mapping.

NeurIPS Conference 2025 Conference Paper

Don't be lazy: CompleteP enables compute-efficient deep transformers

• Nolan Dey
• Bin Zhang
• Lorenzo Noci
• Mufan Li
• Blake Bordelon
• Shane Bergsma
• Cengiz Pehlevan
• Boris Hanin

We study compute efficiency of LLM training when using different parameterizations, i. e. , rules for adjusting model and optimizer hyperparameters (HPs) as model size changes. Some parameterizations fail to transfer optimal base HPs (such as learning rate) across changes in model depth, requiring practitioners to either re-tune these HPs as they scale up (expensive), or accept sub-optimal training when re-tuning is prohibitive. Even when they achieve HP transfer, we develop theory to show parameterizations may still exist in the lazy learning regime where layers learn only features close to their linearization, preventing effective use of depth and nonlinearity. Finally, we identify and adopt the parameterization we call CompleteP that achieves both depth-wise HP transfer and non-lazy learning in all layers. CompleteP enables a wider range of model width/depth ratios to remain compute-efficient, unlocking shapes better suited for different hardware settings and operational contexts. Moreover, CompleteP enables 12-34% compute efficiency improvements over the prior state-of-the-art. All experiments were run on Cerebras CS-3 systems. A minimal implementation is available at https: //github. com/EleutherAI/nanoGPT-mup/tree/completep.

AAAI Conference 2025 Conference Paper

Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation

• Dapeng Li
• Na Lou
• Zhiwei Xu
• Bin Zhang
• Guoliang Fan

A key challenge in multi-agent collaborative tasks is reducing uncertainty about teammates to enhance cooperative performance. Explicit communication methods can reduce uncertainty about teammates, but the associated high communication costs limit their practicality. Alternatively, implicit consensus learning can promote cooperation without incurring communication costs. However, its performance declines significantly when local observations are severely limited. This paper introduces a novel multi-agent learning framework that combines the strengths of these methods. In our framework, agents generate a consensus about the group based on their local observations and then use both the consensus and local observations to produce messages. Since the consensus provides a certain level of global guidance, communication can be disabled when not essential, thereby reducing overhead. Meanwhile, communication can provide supplementary information to the consensus when necessary. Experimental results demonstrate that our algorithm significantly reduces inter-agent communication overhead while ensuring efficient collaboration.

IJCAI Conference 2025 Conference Paper

ILIF: Temporal Inhibitory Leaky Integrate-and-Fire Neuron for Overactivation in Spiking Neural Networks

• Kai Sun
• Peibo Duan
• Levin Kuhlmann
• Beilun Wang
• Bin Zhang

The Spiking Neural Network (SNN) has drawn increasing attention for its energy-efficient, event-driven processing and biological plausibility. To train SNNs via backpropagation, surrogate gradients are used to approximate the non-differentiable spike function, but they only maintain nonzero derivatives within a narrow range of membrane potentials near the firing threshold—referred to as the surrogate gradient support width gamma. We identify a major challenge, termed the dilemma of gamma: a relatively large gamma leads to overactivation, characterized by excessive neuron firing, which in turn increases energy consumption, whereas a small gamma causes vanishing gradients and weakens temporal dependencies. To address this, we propose a temporal Inhibitory Leaky Integrate-and-Fire (ILIF) neuron model, inspired by biological inhibitory mechanisms. This model incorporates interconnected inhibitory units for membrane potential and current, effectively mitigating overactivation while preserving gradient propagation. Theoretical analysis demonstrates ILIF’s effectiveness in overcoming the gamma dilemma, and extensive experiments on multiple datasets show that ILIF improves energy efficiency by reducing firing rates, stabilizes training, and enhances accuracy. The code is available at github. com/kaisun1/ILIF.

TMLR Journal 2025 Journal Article

QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning

• Yilun Kong
• Hangyu Mao
• Zhao Qi
• Bin Zhang
• Jingqing Ruan
• Li Shen
• Yongzhe Chang
• Xueqian Wang

Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization methods only focus on the task-level performance, overlooking the importance of query-preferred prompts, which leads to suboptimal performances. Additionally, these methods rely heavily on frequent interactions with LLMs to obtain feedback for guiding the optimization process, incurring substantial redundant interaction costs. In this paper, we introduce Query-dependent Prompt Optimization ($\textbf{QPO}$), which leverages multi-loop offline reinforcement learning to iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries, thus significantly improving the prompting effect on the large target LLM. We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks, thereby circumventing the expenses of online interactions. Furthermore, we continuously augment the offline dataset with the generated prompts in each loop, as the prompts from the fine-tuned model are supposed to outperform the source prompts in the original dataset. These iterative loops bootstrap the model towards generating optimal prompts. Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.

AAAI Conference 2025 Conference Paper

RUNA: Object-Level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations

• Bin Zhang
• Jinggang Chen
• Xiaoyang Qu
• Guokuan Li
• Kai Lu
• Jiguang Wan
• Jing Xiao
• Jianzong Wang

Enabling object detectors to recognize out-of-distribution (OOD) objects is vital for building reliable systems. A primary obstacle stems from the fact that models frequently do not receive supervisory signals from unfamiliar data, leading to overly confident predictions regarding OOD objects. Despite previous progress that estimates OOD uncertainty based on the detection model and in-distribution (ID) samples, we explore using pre-trained vision-language representations for object-level OOD detection. We first discuss the limitations of applying image-level CLIP-based OOD detection methods to object-level scenarios. Building upon these insights, we propose RUNA, a novel framework that leverages a dual encoder architecture to capture rich contextual information and employs a regional uncertainty alignment mechanism to distinguish ID from OOD objects effectively. We introduce a few-shot fine-tuning approach that aligns region-level semantic representations to further improve the model's capability to discriminate between similar objects. Our experiments show that RUNA substantially surpasses state-of-the-art methods in object-level OOD detection, particularly in challenging scenarios with diverse and complex object instances.

YNIMG Journal 2025 Journal Article

The changes in neural complexity and connectivity in thalamocortical and cortico-cortical systems after propofol-induced unconsciousness in different temporal scales

• Zhenhu Liang
• Luxin Fan
• Bin Zhang
• Wei Shu
• Duan Li
• Xiaoli Li
• Tao Yu

Existing studies have indicated neural activity across diverse temporal and spatial scales. However, the alterations in complexity, functional connectivity, and directional connectivity within the thalamocortical and corticocortical systems across various scales during propofol-induced unconsciousness remain uncertain. We analyzed the stereo-electroencephalography (SEEG) from wakefulness to unconsciousness among the brain regions of the prefrontal cortex, temporal lobe, and anterior nucleus of the thalamus. The complexity (examined by permutation entropy (PE)), functional connectivity (permutation mutual information (PMI)), and directional connectivity (symbolic conditional mutual information (SCMI) and directionality index (DI)) were calculated across various scales. In the lower-band frequency (0.1-45 Hz) SEEG, after the loss of consciousness, PE significantly decreased (p < 0.001) in all regions and scales, except for the thalamus, which remained relatively unchanged at large scales (τ=32 ms). Following the loss of consciousness, inter-regional PMI either significantly increased or remained stable across different scales (τ=4 ms to 32 ms). During the unconscious state, SCMI between brain regions exhibited inconsistent changes across scales. In the late unconscious stage, the inter-regional DI across all scales indicated a shift from a balanced state of information flow between brain regions to a pattern where the prefrontal cortex and thalamus drive the temporal lobe. Our findings demonstrate that propofol-induced unconsciousness is associated with reduced cortical complexity, diverse functional connectivity, and a disrupted balance of information integration among thalamocortical and cortico-cortical systems. This study enhances the theoretical understanding of anesthetic-induced loss of consciousness by elucidating the scale- and region-specific effects of propofol on thalamocortical and cortico-cortical systems.

AAMAS Conference 2025 Conference Paper

Unveiling Decision Intention for Cooperative Multi-Agent Reinforcement Learning

• Zeren Zhang
• Zhiwei Xu
• Guangchong Zhou
• Dapeng Li
• Bin Zhang
• Guoliang Fan

For cooperative multi-agent reinforcement learning, various methods have been proposed to enhance the collaborative strategy capabilities of agents. However, when agents make decisions, humans have no knowledge of their subsequent decision-making intentions or sub-goals. This lack of understanding hinders human comprehension of agent strategies and further research on agents. Currently, there are limited relevant studies. To address this problem, we propose a novel framework which can generate the decision intention of agents. We first formalize this problem and use states crucial to the task to express the decision intentions of agents. Then, we introduce the polarization index to measure the importance of states and select them for training. Finally, we learn the decision intentions through a diffusion model with rapid generation capability and generate them during the decision-making process. This study sheds light on the problem of agent decision intention and enhances the transparency of agent strategies, facilitating deeper research on This work is licensed under a Creative Commons Attribution International 4. 0 License. Proc. of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025), Y. Vorobeychik, S. Das, A. Nowé (eds.), May 19 – 23, 2025, Detroit, Michigan, USA. © 2025 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). agents. The experimental results demonstrate the effectiveness of our approach.

EAAI Journal 2024 Journal Article

A dual-time dual-population multi-objective evolutionary algorithm with application to the portfolio optimization problem

• Yingjie Song
• Lihuan Han
• Bin Zhang
• Wu Deng

The article proposes a dual-time dual-population multi-objective evolutionary algorithm, DTDP-EAMO, to address the challenges faced by multi-objective differential evolution algorithms in solving complex optimization problems, such as weakened late-stage search capability, susceptibility to local optima, and insufficient diversity. Firstly, DTDP-EAMO divides the population into three sub-populations using fast nondominated sorting. Then, it introduces a dual-stage and multi-population adaptive mutation strategy to maintain the convergence and diversity of each sub-population. Meanwhile, a dual external archive mechanism is introduced to enable the population to escape local optima and facilitate information exchange between sub-populations through archiving high-quality solutions from both stages. Finally, the individuals in the external archive are sorted, and high-quality solutions are selected and recombined to generate a new population. To demonstrate the effectiveness of DTDP-EAMO, fourteen test functions and a portfolio optimization problem are selected. Experimental results show that the algorithm's overall performance is superior to three comparative algorithms. Furthermore, practical application results demonstrate DTDP-EAMO's ability to reduce risk and increase returns in portfolio optimization problems, further confirming its effectiveness and feasibility. DTDP-EAMO outperforms comparative algorithms in convergence and distribution, indicating higher accuracy and superiority in solving portfolio models.

AIIM Journal 2024 Journal Article

Corrigendum to “DeepGA for automatically estimating fetal gestational age through ultrasound imaging” [Artif. Intell. Med. 135 (2023) 102453]

• Tingting Dan
• Xijie Chen
• Miao He
• Hongmei Guo
• Xiaoqin He
• Jiazhou Chen
• Jianbo Xian
• Yu Hu

AAAI Conference 2024 Conference Paper

DMMR: Cross-Subject Domain Generalization for EEG-Based Emotion Recognition via Denoising Mixed Mutual Reconstruction

• Yiming Wang
• Bin Zhang
• Yujiao Tang

Electroencephalography (EEG) has proven to be effective in emotion analysis. However, current methods struggle with individual variations, complicating the generalization of models trained on data from source subjects to unseen target subjects. To tackle this issue, we propose the Denoising Mixed Mutual Reconstruction (DMMR) model, employing a two-stage pre-training followed by fine-tuning approach. During the pre-training phase, DMMR leverages self-supervised learning through a multi-decoder autoencoder, which encodes and reconstructs features of one subject, aiming to generate features resembling those from other subjects within the same category, thereby encouraging the encoder to learn subject-invariant features. We introduce a hidden-layer mixed data augmentation approach to mitigate the limitations posed by the scarcity of source data, thereby extending the method to a two-stage process. To bolster stability against noise, we incorporate a noise injection method, named “Time Steps Shuffling”, into the input data. During the fine-tuning phase, an emotion classifier is integrated to extract emotion-related features. Experimental accuracy on the SEED and SEED-IV datasets reached 88.27% (±5.62) and 72.70% (±8.01), respectively, demonstrating state-of-the-art and comparable performance, thereby showcasing the superiority of DMMR. The proposed data augmentation and noise injection methods were observed to complementarily enhance accuracy and stability, thus alleviating the aforementioned issues.

AAMAS Conference 2024 Conference Paper

From Explicit Communication to Tacit Cooperation: A Novel Paradigm for Cooperative MARL

• Dapeng Li
• Zhiwei Xu
• Bin Zhang
• Guangchong Zhou
• Zeren Zhang
• Guoliang Fan

Centralized training with decentralized execution (CTDE) is a widely used learning paradigm that has achieved significant success in complex tasks. Drawing inspiration from human team cooperative learning, we propose a novel paradigm that facilitates a gradual shift from explicit communication to tacit cooperation. In the initial training stage, we promote cooperation by sharing relevant information among agents and concurrently reconstructing this information using each agent’s local trajectory in a self-supervised way. We then combine the explicitly communicated information with the reconstructed information to obtain mixed information. Throughout the training process, we progressively decrease the proportion of explicitly communicated information, facilitating a seamless transition to fully decentralized execution without communication.

AAAI Conference 2024 Conference Paper

Online Boosting Adaptive Learning under Concept Drift for Multistream Classification

• En Yu
• Jie Lu
• Bin Zhang
• Guangquan Zhang

Multistream classification poses significant challenges due to the necessity for rapid adaptation in dynamic streaming processes with concept drift. Despite the growing research outcomes in this area, there has been a notable oversight regarding the temporal dynamic relationships between these streams, leading to the issue of negative transfer arising from irrelevant data. In this paper, we propose a novel Online Boosting Adaptive Learning (OBAL) method that effectively addresses this limitation by adaptively learning the dynamic correlation among different streams. Specifically, OBAL operates in a dual-phase mechanism, in the first of which we design an Adaptive COvariate Shift Adaptation (AdaCOSA) algorithm to construct an initialized ensemble model using archived data from various source streams, thus mitigating the covariate shift while learning the dynamic correlations via an adaptive re-weighting strategy. During the online process, we employ a Gaussian Mixture Model-based weighting mechanism, which is seamlessly integrated with the acquired correlations via AdaCOSA to effectively handle asynchronous drift. This approach significantly improves the predictive performance and stability of the target stream. We conduct comprehensive experiments on several synthetic and real-world data streams, encompassing various drifting scenarios and types. The results clearly demonstrate that OBAL achieves remarkable advancements in addressing multistream classification problems by effectively leveraging positive knowledge derived from multiple sources.

AAMAS Conference 2024 Conference Paper

PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning

• Hangyu Mao
• Rui Zhao
• Ziyue Li
• Zhiwei Xu
• Hao Chen
• Yiqun Chen
• Bin Zhang
• Zhen Xiao

Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work studies the former. Specifically, the Perception and Decision-making Interleaving Transformer (PDiT) network is proposed, which cascades two Transformers in a very natural way: the perceiving one focuses on the environmental perception by processing the observation at the patch level, whereas the deciding one pays attention to the decisionmaking by conditioning on the history of the desired returns, the perceiver’s outputs, and the actions. Such a network design is generally applicable to a lot of deep RL settings, e. g. , both the online and offline RL algorithms under environments with either image observations, proprioception observations, or hybrid image-language observations. Extensive experiments show that PDiT can not only achieve superior performance than strong baselines in different settings but also extract explainable feature representations. Our code is available at https: //github. com/maohangyu/PDiT.

IJCAI Conference 2024 Conference Paper

PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning

• Yiqun Chen
• Hangyu Mao
• Jiaxin Mao
• Shiguang Wu
• Tianle Zhang
• Bin Zhang
• Wei Yang
• Hongxing Chang

Centralized Training with Decentralized Execution (CTDE) has emerged as a widely adopted paradigm in multi-agent reinforcement learning, emphasizing the utilization of global information for learning an enhanced joint Q-function or centralized critic. In contrast, our investigation delves into harnessing global information to directly enhance individual Q-functions or individual actors. Notably, we discover that applying identical global information universally across all agents proves insufficient for optimal performance. Consequently, we advocate for the customization of global information tailored to each agent, creating agent-personalized global information to bolster overall performance. Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information. This distilled information is then utilized during decentralized execution, resulting in minimal performance degradation. PTDE can be seamless integrated with state-of-the-art algorithms, leading to notable performance enhancements across diverse benchmarks, including the SMAC benchmark, Google Research Football (GRF) benchmark, and Learning to Rank (LTR) task.

IJCAI Conference 2024 Conference Paper

Task-Agnostic Self-Distillation for Few-Shot Action Recognition

• Bin Zhang
• Yuanjie Dang
• Peng Chen
• Ronghua Liang
• Nan Gao
• Ruohong Huan
• Xiaofei He

Task-oriented matching is one of the core aspects of few-shot Action Recognition. Most previous works leverage the metric features within the support and query sets of individual tasks, without considering the metric information across different matching tasks. This oversight represents a significant limitation in this task. Specifically, the task-specific metric feature can decrease the generalization ability and ignore the general matching feature applicable across different tasks. To address these challenges, we propose a novel meta-distillation framework for few-shot action recognition that learns the task-agnostic metric features and generalizes them to different tasks. First, to extract the task-agnostic metric information, we design a task-based self-distillation framework to learn the metric features from the training process progressively. Additionally, to enable the model with fine-grained matching capabilities, we design a multi-dimensional distillation module that extracts more detailed relations from the temporal, spatial, and channel dimensions within video pairs and improves the representative performance of metric features for each individual task. After that, the few-shot predictions can be obtained by feeding the embedded task-agnostic metric features to a common feature matcher. Extensive experimental results on standard datasets demonstrate our method’s superior performance compared to existing state-of-the-art methods.

EAAI Journal 2023 Journal Article

An enhanced distributed differential evolution algorithm for portfolio optimization problems

• Yingjie Song
• Gaoyang Zhao
• Bin Zhang
• Huayue Chen
• Wuquan Deng
• Wu Deng

The population structure of differential evolution (DE) algorithm cannot maintain the diversity of the population to the greatest extent and help the population avoid to fall into the local optima in time. In this paper, a co-evolutionary multi-swarm adaptive differential evolution algorithm, namely ECMADE is proposed to solve the premature convergence and search stagnation. First of all, in terms of population structure, based on the parallel distributed framework, ECMADE randomly and evenly divides the population into exploration subpopulation, development subpopulation, and auxiliary subpopulation, and introduces an adaptive information exchange mechanism so that subpopulations can escape local optima in time. Then, a multi-operator parallel search strategy is proposed to keep population diversity and meet the optimization needs of different problems. Finally, an adaptive adjustment mechanism of control parameters is developed, through recent elite parameter archive and weight distribution to fully mine successful parameter information, and generate control parameters with a high success rate for the current evolutionary stage. In order to prove the effectiveness of the ECMADE, 10 test functions and portfolio optimization problem are selected in here. The experiment results show that the ECMADE can effectively solve these test functions, the accuracy and efficiency is superior to those of two classical DE algorithms. The actual application results show that the ECMADE can significantly improve the ability of portfolio to resist extreme losses, which proves the effectiveness and feasibility of the ECMADE once again. The ECMADE has better optimization performance by comparing with some well-known algorithms in term of the solution quality, robustness and space distribution. It provides a new algorithm for solving complex optimization problems.

AAAI Conference 2023 Conference Paper

Consensus Learning for Cooperative Multi-Agent Reinforcement Learning

• Zhiwei Xu
• Bin Zhang
• Dapeng Li
• Zeren Zhang
• Guangchong Zhou
• Hao Chen
• Guoliang Fan

Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During the centralized training, agents can be guided by the same signals, such as the global state. However, agents lack the shared signal and choose actions given local observations during execution. Inspired by viewpoint invariance and contrastive learning, we propose consensus learning for cooperative multi-agent reinforcement learning in this study. Although based on local observations, different agents can infer the same consensus in discrete spaces without communication. We feed the inferred one-hot consensus to the network of agents as an explicit input in a decentralized way, thereby fostering their cooperative spirit. With minor model modifications, our suggested framework can be extended to a variety of multi-agent reinforcement learning algorithms. Moreover, we carry out these variants on some fully cooperative tasks and get convincing results.

AIIM Journal 2023 Journal Article

DeepGA for automatically estimating fetal gestational age through ultrasound imaging

• Tingting Dan
• Xijie Chen
• Miao He
• Hongmei Guo
• Xiaoqin He
• Jiazhou Chen
• Jianbo Xian
• Yu Hu

Accurate estimation of gestational age (GA) is vital for identifying fetal abnormalities. Conventionally, GA is estimated by measuring the morphology of the cranium, abdomen, and femur manually and inputting them into the classic Hadlock formula to assess fetal growth. However, this procedure incurs considerable overhead and suffers from bias caused by the operators, yielding suboptimal estimations. To address this challenge, we develop an automatic DeepGA model to achieve fully automatic GA prediction in an end-to-end manner. Our model uses a deep segmentation model (DeepSeg) to accurately identify and segment three critical tissues, including the cranium, abdomen, and femur, in which their morphology is automatically extracted. After that, we are able to directly estimate the GA via a deep regression model (DeepReg). We evaluate DeepGA on a large dataset, including 10, 413 ultrasound images from 7113 subjects. It achieves superior performance over the traditional measurement approach, with a mean absolute estimation error (MAE) of 5 days. Our DeepGA model is a novel automatic solution on the basis of artificial intelligence learning that can help radiologists improve the performance of GA estimation in various clinical scenarios, thereby enhancing the efficiency of prenatal examinations.

NeurIPS Conference 2023 Conference Paper

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL

• Zhiwei Xu
• Bin Zhang
• Dapeng Li
• Guangchong Zhou
• Zeren Zhang
• Guoliang Fan

Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise. Each agent consists of an ego policy for action selection and an alter ego value function to solve the credit assignment problem. The value function factorization can ignore the IGM assumption by utilizing an explicit search procedure. On the basis of the above, we also suggest a novel anti-ego exploration mechanism to avoid the algorithm becoming stuck in a local optimum. As the first fully IGM-free value decomposition method, our proposed framework achieves desirable performance in various cooperative tasks.

AAAI Conference 2023 Conference Paper

HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism

• Zhiwei Xu
• Yunpeng Bai
• Bin Zhang
• Dapeng Li
• Guoliang Fan

Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods. Inspired by the intra-level and inter-level coordination in the human nervous system, we propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for fully cooperative multi-agent problems. To address the instability arising from the concurrent optimization of policies between various levels and agents, we introduce the dual coordination mechanism of inter-level and inter-agent strategies by designing reward functions in a two-level hierarchy. HAVEN does not require domain knowledge and pre-training, and can be applied to any value decomposition variant. Our method achieves desirable results on different decentralized partially observable Markov decision process domains and outperforms other popular multi-agent hierarchical reinforcement learning algorithms.

IJCAI Conference 2023 Conference Paper

Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning

• Bin Zhang
• Lijuan Li
• Zhiwei Xu
• Dapeng Li
• Guoliang Fan

In multi-agent reinforcement learning (MARL), self-interested agents attempt to establish equilibrium and achieve coordination depending on game structure. However, existing MARL approaches are mostly bound by the simultaneous actions of all agents in the Markov game (MG) framework, and few works consider the formation of equilibrium strategies via asynchronous action coordination. In view of the advantages of Stackelberg equilibrium (SE) over Nash equilibrium, we construct a spatio-temporal sequential decision-making structure derived from the MG and propose an N-level policy model based on a conditional hypernetwork shared by all agents. This approach allows for asymmetric training with symmetric execution, with each agent responding optimally conditioned on the decisions made by superior agents. Agents can learn heterogeneous SE policies while still maintaining parameter sharing, which leads to reduced cost for learning and storage and enhanced scalability as the number of agents increases. Experiments demonstrate that our method effectively converges to the SE policies in repeated matrix game scenarios, and performs admirably in immensely complex settings including cooperative tasks and mixed tasks.

JBHI Journal 2023 Journal Article

Modality-Specific Segmentation Network for Lung Tumor Segmentation in PET-CT Images

• Dehui Xiang
• Bin Zhang
• Yuxuan Lu
• Shengming Deng

Lung tumor segmentation in PET-CT images plays an important role to assist physicians in clinical application to accurately diagnose and treat lung cancer. However, it is still a challenging task in medical image processing field. Due to respiration and movement, the lung tumor varies largely in PET images and CT images. Even the two images are almost simultaneously collected and registered, the shape and size of lung tumors in PET-CT images are different from each other. To address these issues, a modality-specific segmentation network (MoSNet) is proposed for lung tumor segmentation in PET-CT images. MoSNet can simultaneously segment the modality-specific lung tumor in PET images and CT images. MoSNet learns a modality-specific representation to describe the inconsistency between PET images and CT images and a modality-fused representation to encode the common feature of lung tumor in PET images and CT images. An adversarial method is proposed to minimize an approximate modality discrepancy through an adversarial objective with respect to a modality discriminator and reserve modality-common representation. This improves the representation power of the network for modality-specific lung tumor segmentation in PET images and CT images. The novelty of MoSNet is its ability to produce a modality-specific map that explicitly quantifies the modality-specific weights for the features in each modality. To demonstrate the superiority of our method, MoSNet is validated in 126 PET-CT images with NSCLC. Experimental results show that MoSNet outperforms state-of-the-art lung tumor segmentation methods.

YNICL Journal 2023 Journal Article

MRI histogram analysis of tumor-infiltrating CD8+ T cell levels in patients with glioblastoma

• Caiqiang Xue
• Qing Zhou
• Peng Zhang
• Bin Zhang
• Qiu Sun
• Shenglin Li
• Juan Deng
• Xianwang Liu

OBJECTIVE: To investigate the utility of preoperative magnetic resonance imaging histogram analysis for evaluating tumor-infiltrating CD8+ T cells in patients with glioblastoma (GBM). METHODS: We retrospectively analyzed the pathological and imaging data of 61 patients with GBM confirmed by surgery and pathology. Moreover, the levels of tumor-infiltrating CD8+ T cells in tumor tissue samples obtained from the patients were quantified through immunohistochemical staining and evaluated with respect to overall survival. The patients were divided into the high and low CD8 expression groups. Preoperative T1-weighted contrast-enhanced (T1C) histogram parameters of patients with GBM were extracted using Firevoxel software. We investigated the correlation between the histogram feature parameters and CD8+ T cells. We performed statistical analyses of the T1C histogram parameters in both groups and identified characteristic parameters with significant between-group differences. Additionally, we performed a receiver operating characteristic curve (ROC) analysis to determine the predictive utility of these parameters. RESULTS: The levels of tumor-infiltrating CD8+ T cells were positively associated with overall survival in patients with GBM (P = 0.0156). Among the T1C histogram features, the mean, 5th, 10th, 25th, and 50th percentiles were negatively correlated with the levels of CD8+ T cells. Moreover, the coefficient of variation (CV) was positively correlated with the levels of CD8+ T cells (all P < 0.05). There was a significant between-group difference in the CV, 1st, 5th, 10th, 25th, and 50th percentiles (all p < 0.05). The ROC curve analysis revealed that the CV had the highest AUC value (0.783; 95% confidence interval: 0.658-0.878), with sensitivity and specificity values of 0.784 and 0.750, respectively, for distinguishing between the groups. CONCLUSIONS: The preoperative T1C histogram have additional value for the levels of tumor-infiltrating CD8+ T cells in patients with GBM.

EAAI Journal 2023 Journal Article

TCGNN: Packet-grained network traffic classification via Graph Neural Networks

• Guangwu Hu
• Xi Xiao
• Meng Shen
• Bin Zhang
• Xia Yan
• Yunxia Liu

Network traffic classification is the fundamental and vital function for network management, network security and so on. With the traffic scenarios becoming more and more complex, current commonly used practices, e. g. , port-based and payload-based classification methods, can hardly work. Even though the new emerging resorts, i. e. , machine learning or deep learning methods, have increased classification accuracy, the performance is still under improvement. To improve the classification accuracy and performance, we propose a novel Graph Neural Network (GNN) based Traffic Classification proposal named TCGNN considering the insight of observing packets from a graph aspect. TCGNN first transforms each network packet into an undirected graph. Then it adopts a two-layer graph convolutional network with three different aggregation strategies so as to learn the latent application representation from the packet-transformed graph. Finally, relying on GNN’s powerful ability in learning graph representation, TCGNN can identify unknown network packets with an extremely high accuracy rate. Extensive experiments on two real-world traffic classification datasets demonstrate the superior effectiveness of TCGNN over the existing packet-grained traffic classification methods.

NeurIPS Conference 2022 Conference Paper

Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning

• Zhiwei Xu
• Dapeng Li
• Bin Zhang
• Yuan Zhan
• Yunpeng Baiia
• Guoliang Fan

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding error may hinder the learning process when model-based methods are applied to multi-agent tasks. This paper proposes an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states in the latent space, making agents have the foresight. Our approach can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in different partially observable Markov decision process domains.

AAAI Conference 2022 Conference Paper

SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems

• Harrison Lee
• Raghav Gupta
• Abhinav Rastogi
• Yuan Cao
• Bin Zhang
• Yonghui Wu

Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling models to support any service in zero-shot through schemas, which describe service APIs to models in natural language. We explore the robustness of dialogue systems to linguistic variations in schemas by designing SGD-X - a benchmark extending SGD with semantically similar yet stylistically diverse variants for every schema. We observe that two top state tracking models fail to generalize well across schema variants, measured by joint goal accuracy and a novel metric for measuring schema sensitivity. Additionally, we present a simple model-agnostic data augmentation method to improve schema robustness.

AAMAS Conference 2022 Conference Paper

SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning

• Zhiwei Xu
• Yunpeng Bai
• Dapeng Li
• Bin Zhang
• Guoliang Fan

As one of the solutions to the decentralized partially observable Markov decision process (Dec-POMDP) problems, the value decomposition method has achieved significant results recently. However, most value decomposition methods require the fully observable state of the environment during training, but this is not feasible in some scenarios where only incomplete and noisy observations can be obtained. Therefore, we propose a novel value decomposition framework, named State Inference for value DEcomposition (SIDE), which eliminates the need to know the global state by simultaneously seeking solutions to the two problems of optimal control and state inference. SIDE can be extended to any value decomposition method to tackle partially observable problems. By comparing with the performance of different algorithms in Star- Craft II micromanagement tasks, we verified that though without accessible states, SIDE can infer the current state that contributes to the reinforcement learning process based on past local observations and even achieve superior results to many baselines in some complex scenarios.

AAAI Conference 2021 Conference Paper

Fast Multi-view Discrete Clustering with Anchor Graphs

• Qianyao Qiang
• Bin Zhang
• Fei Wang
• Feiping Nie

Generally, the existing graph-based multi-view clustering models consists of two steps: (1) graph construction; (2) eigendecomposition on the graph Laplacian matrix to compute a continuous cluster assignment matrix, followed by a postprocessing algorithm to get the discrete one. However, both the graph construction and eigen-decomposition are timeconsuming, and the two-stage process may deviate from directly solving the primal problem. To this end, we propose Fast Multi-view Discrete Clustering (FMDC) with anchor graphs, focusing on directly solving the spectral clustering problem with a small time cost. We efficiently generate representative anchors and construct anchor graphs on different views. The discrete cluster assignment matrix is directly obtained by performing clustering on the automatically aggregated graph. FMDC has a linear computational complexity with respect to the data scale, which is a significant improvement compared to the quadratic one. Extensive experiments on benchmark datasets demonstrate its efficiency and effectiveness.

EAAI Journal 2020 Journal Article

A review of machine learning for new generation smart dispatch in power systems

• Linfei Yin
• Qi Gao
• Lulin Zhao
• Bin Zhang
• Tao Wang
• Shengyuan Li
• Hui Liu

This paper analyzes the characteristics and challenges of the new generation smart dispatch systems, and proposes the framework of smart dispatch. Secondly, the development of the new generation artificial intelligence technology is represented, especially the development of machine learning algorithms. Thirdly, the applications of machine learning in power systems, e. g. smart generation control, optimal power flow, security assessment, smart dispatch, are listed. Finally, the framework of dispatching robot technology based on parallel learning is present.

YNICL Journal 2020 Journal Article

Systems modeling of white matter microstructural abnormalities in Alzheimer's disease

• Emrin Horgusluoglu-Moloch
• Gaoyu Xiao
• Minghui Wang
• Qian Wang
• Xianxiao Zhou
• Kwangsik Nho
• Andrew J. Saykin
• Eric Schadt

INTRODUCTION: Microstructural abnormalities in white matter (WM) are often reported in Alzheimer's disease (AD). However, it is unclear which brain regions have the strongest WM changes in presymptomatic AD and what biological processes underlie WM abnormality during disease progression. METHODS: We developed a systems biology framework to integrate matched diffusion tensor imaging (DTI), genetic and transcriptomic data to investigate regional vulnerability to AD and identify genetic risk factors and gene subnetworks underlying WM abnormality in AD. RESULTS: We quantified regional WM abnormality and identified most vulnerable brain regions. A SNP rs2203712 in CELF1 was most significantly associated with several DTI-derived features in the hippocampus, the top ranked brain region. An immune response gene subnetwork in the blood was most correlated with DTI features across all the brain regions. DISCUSSION: Incorporation of image analysis with gene network analysis enhances our understanding of disease progression and facilitates identification of novel therapeutic strategies for AD.

JBHI Journal 2017 Journal Article

Single-Channel Sparse Non-Negative Blind Source Separation Method for Automatic 3-D Delineation of Lung Tumor in PET Images

• Ivica Kopriva
• Wei Ju
• Bin Zhang
• Fei Shi
• Dehui Xiang
• Kai Yu
• Ximing Wang
• Ulas Bagci

In this paper, we propose a novel method for single-channel blind separation of nonoverlapped sources and, to the best of our knowledge, apply it for the first time to automatic segmentation of lung tumors in positron emission tomography (PET) images. Our approach first converts a 3-D PET image into a pseudo-multichannel image. Afterward, regularization free sparseness constrained non-negative matrix factorization is used to separate tumor from other tissues. By using complexity based criterion, we select tumor component as the one with minimal complexity. We have compared the proposed method with threshold based on 40% and 50% maximum standardized uptake value (SUV), graph cuts (GC), random walks (RW), and affinity propagation (AP) algorithms on 18 nonsmall cell lung cancer datasets with respect to ground truth (GT) provided by two radiologists. Dice similarity coefficient averaged with respect to two GTs is: 0. 78 ± 0. 12 by the proposed algorithm, 0. 78 ± 0. 1 by GC, 0. 77 ± 0. 13 by AP, 0. 77 ± 0. 07 by RW, and 0. 75 ± 0. 13 by 50% maximum SUV threshold. Since the proposed method achieved performance comparable with interactive methods, considering the unique challenges of lung tumor segmentation from PET images, our findings support possibility of using our fully automated method in routine clinics. The source codes will be available at www. mipav. net/English/research/research. html.

JBHI Journal 2013 Journal Article

360° Fourier Transform Profilometry in Surface Reconstruction for Fluorescence Molecular Tomography

• Bi'er Shi
• Bin Zhang
• Fei Liu
• Jianwen Luo
• Jing Bai

Fluorescence molecular tomography (FMT) is an emerging tool in the observation of diseases. A fast and accurate surface reconstruction of the experimental object is needed as a boundary constraint for FMT reconstruction. In this paper, an automatic, noncontact, and 3-D surface reconstruction method named 360° Fourier transform profilometry (FTP) is proposed to reconstruct 3-D surface profiles for FMT system. This method can reconstruct 360° integrated surface profiles utilizing the single-frame FTP at different angles. Results show that the relative mean error of the surface reconstruction of this method is less than 1. 4% in phantom experiments, and is no more than 2. 9% in mouse experiments in vivo. Compared with the Radon transform method, the proposed method reduces the computation time by more than 90% with a minimal error increase. At last, a combined 360° FTP/FMT experiment is conducted on a nude mouse. Not only can the 360° FTP system operate with the FMT system simultaneously, but it can also help to monitor the status of animals. Moreover, the 360° FTP system is independent of FMT system and can be performed to reconstruct the surface by itself.

IJCAI Conference 2009 Conference Paper

• Fei Wang
• Bin Zhang
• Ta-Hsin Li
• Wen Jun Yin
• Jin Dong
• Tao Li

In this paper, we consider a general problem of semi-supervised preference learning, in which we assume that we have the information of the extreme cases and some ordered constraints, our goal is to learn the unknown preferences of the other places. Taking the potential housing place selection problem as an example, we have many candidate places together with their associated information (e. g. , position, environment), and we know some extreme examples (i. e. several places are perfect for building a house, and several places are the worst that cannot build a house there), and we know some partially ordered constraints (i. e. for two places, which place is better), then how can we judge the preference of one potential place whose preference is unknown beforehand? We propose a Bayesian framework based on Gaussian process to tackle this problem, from which we not only solve for the unknown preferences, but also the hyperparameters contained in our model.

AAAI Conference 2008 Conference Paper

Classification by Discriminative Regularization

• Bin Zhang
• Ta-Hsin Li

Classification is one of the most fundamental problems in machine learning, which aims to separate the data from different classes as far away as possible. A common way to get a good classification function is to minimize its empirical prediction loss or structural loss. In this paper, we point out that we can also enhance the discriminality of those classifiers by further incorporating the discriminative information contained in the data set as a prior into the classifier construction process. In such a way, we will show that the constructed classifiers will be more powerful, and this will also be validated by the final empirical study on several benchmark data sets.