Arrow Research search

Author name cluster

Yue Zhao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

41 papers
2 author rows

Possible papers

41

TMLR Journal 2026 Journal Article

Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning

  • Yuehan Qin
  • Li Li
  • Yi Nian
  • Xinyan Velocity Yu
  • Yue Zhao
  • Xuezhe Ma

Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially when a user query includes one or more false premises—claims that contradict established facts. Such premises can mislead LLMs into offering fabricated or misleading details. Existing approaches include pretraining, fine-tuning, and inference-time techniques that often rely on access to logits or address hallucinations after they occur. These methods tend to be computationally expensive, require extensive training data, or lack proactive mechanisms to prevent hallucination before generation, limiting their efficiency in real-time applications. We propose a retrieval-based framework that identifies and addresses false premises before generation. Our method first transforms a user’s query into a logical representation, then applies retrieval-augmented generation (RAG) to assess the validity of each premise using factual sources. Finally, we incorporate the verification results into the LLM’s prompt to maintain factual consistency in the final output. Experiments show that this approach effectively reduces hallucinations, improves factual accuracy, and does not require access to model logits or large-scale fine-tuning.

PDF Details

EAAI Journal 2026 Journal Article

Ground-to-Aerial Scene Adaptation: Unsupervised drone video action recognition via domain adaptation

  • Feng Yang
  • Zhijia Li
  • Xi Liu
  • Fulin Luo
  • Anyong Qin
  • Tiecheng Song
  • Yue Zhao
  • Chenqiang Gao

The unsupervised domain adaptation (UDA) methods can well address the problem of scarce annotated videos in drone video action recognition by transferring knowledge from rich ground-camera datasets. However, existing UDA video methods are subject to huge domain shifts: changes in perspective and scale for key areas result in significant differences between ground-camera videos and drone videos, posing distinct alignment challenges. Moreover, the high similarity between classes in drone videos further complicates the learning of class-discriminant information. To deal with these issues, we propose a novel framework called Ground-to-Aerial Scene Adaptation (GASA). To enhance the learning of class-discriminant information, we propose a View-Independent Attention (VIA) module that learns view-independent attention maps and generates discriminative features of action in different domains. Then, a contrastive loss is used to pull the samples from the same category closer in the feature space for semantic alignment, improving the discrimination of target domain classes. Furthermore, we design a novel relation-weighted alignment loss to learn domain-invariant information and focus on challenging samples for better domain alignment. We report the results on Kinetics → NEC-Drone benchmark and Kinetics → UAV-Human dataset, which illustrates the superior performance of our proposed approach. The code is available at https: //github. com/lzjjia/GASA.

Details DOI

AAAI Conference 2026 Conference Paper

KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing

  • Zhifei Li
  • Lifan Chen
  • Jiali Yi
  • Xiaoju Hou
  • Yue Zhao
  • Wenxin Huang
  • Miao Zhang
  • Kui Xiao

Knowledge Tracing (KT) aims to dynamically model a student’s mastery of knowledge concepts based on their historical learning interactions. Most current methods rely on single-point estimates, which cannot distinguish true ability from outburst or carelessness, creating ambiguity in judging mastery. To address this issue, we propose a Knowledge Mastery-State Disambiguation for Knowledge Tracing model (KeenKT), which represents a student’s knowledge state at each interaction using a Normal-Inverse-Gaussian (NIG) distribution, thereby capturing the fluctuations in student learning behaviors. Furthermore, we design an NIG-distance-based attention mechanism to model the dynamic evolution of the knowledge state. In addition, we introduce a diffusion-based denoising reconstruction loss and a distributional contrastive learning loss to enhance the model’s robustness. Extensive experiments on six public datasets demonstrate that KeenKT outperforms state-of-the-art KT models in terms of prediction accuracy and sensitivity to behavioral fluctuations. The proposed method yields the maximum AUC improvement of 5.85% and the maximum ACC improvement of 6.89%.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MacVQA: Adaptive Memory Allocation and Global Noise Filtering for Continual Visual Question Answering

  • Zhifei Li
  • Yiran Wang
  • Chenyi Xiong
  • Yujing Xia
  • Xiaoju Hou
  • Yue Zhao
  • Miao Zhang
  • Kui Xiao

Visual Question Answering (VQA) requires models to reason over multimodal information, combining visual and textual data. With the development of continual learning, significant progress has been made in retaining knowledge and adapting to new information in the VQA domain. However, current methods often struggle with balancing knowledge retention, adaptation, and robust feature representation. To address these challenges, we propose a novel framework with adaptive memory allocation and global noise filtering called MacVQA for visual question answering. MacVQA fuses visual and question information while filtering noise to ensure robust representations, and employs prototype-based memory allocation to optimize feature quality and memory usage. These designs enable MacVQA to balance knowledge acquisition, retention, and compositional generalization in continual VQA learning. Experiments on ten continual VQA tasks show that MacVQA outperforms existing baselines, achieving 43.38% average accuracy and 2.32% average forgetting on standard tasks, and 42.53% average accuracy and 3.60% average forgetting on novel composition tasks.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Mitigating Hallucinations in Large Language Models via Causal Reasoning

  • Yuangang Li
  • Yiqing Shen
  • Yi Nian
  • Jiechao Gao
  • Ziyi Wang
  • Chenxiao Yu
  • Li Li
  • Jie Wang

Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilities and such hallucinations. However, existing reasoning approaches in LLMs, such as Chain-of-Thought (CoT) and its graph-based variants, operate at the linguistic token level rather than modeling the underlying causal relationships between variables, lacking the ability to represent conditional independencies or satisfy causal identification assumptions. To bridge this gap, we introduce causal-DAG construction and reasoning (CDCR-SFT), a supervised fine-tuning framework that trains LLMs to explicitly construct variable-level directed acyclic graph (DAG) and then perform reasoning over it. Moreover, we present a dataset comprising 25,368 samples (CausalDR), where each sample includes an input question, explicit causal DAG, graph-based reasoning trace, and validated answer. Experiments on four LLMs across eight tasks show that CDCR-SFT improves the causal reasoning capability with the state-of-the-art 95.33% accuracy on CLADDER (surpassing human performance of 94.8% for the first time) and reduces the hallucination on HaluEval with 10% improvements. It demonstrates that explicit causal structure modeling in LLMs can effectively mitigate logical inconsistencies in LLM outputs.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MyGram: Modality-aware Graph Transformer with Global Distribution for Multi-modal Entity Alignment

  • Zhifei Li
  • Ziyue Qin
  • Xiangyu Luo
  • Xiaoju Hou
  • Yue Zhao
  • Miao Zhang
  • Zhifang Huang
  • Kui Xiao

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing methods may overlook the structural contextual information within each modality, making them vulnerable to interference from shallow features. To address these challenges, we propose MyGram, a \textbf{m}odalit\textbf{y}-aware \textbf{gra}ph transformer with global distribution for \textbf{m}ulti-modal entity alignment. Specifically, we develop a modality diffusion learning module to capture deep structural contextual information within modalities and enable fine-grained multi-modal fusion. In addition, we introduce a Gram Loss that acts as a regularization constraint by minimizing the volume of a 4-dimensional parallelotope formed by multi-modal features, thereby achieving global distribution consistency across modalities. We conduct experiments on five public datasets. Results show that MyGram outperforms baseline models, achieving a maximum improvement of 4.8\% in Hits@1 on FBDB15K, 9.9\% on FBYG15K, and 4.3\% on DBP15K.

PDF Details DOI

TIST Journal 2025 Journal Article

AEKG4APT: An AI-Enhanced Knowledge Graph for Advanced Persistent Threats with Large Language Model Analysis

  • Yinghai Zhou
  • Ziyu Wang
  • Yunxin Jiang
  • Bingqi Ma
  • Rui Wang
  • Yuan Liu
  • Yue Zhao
  • Zhihong Tian

This paper introduces AEKG4APT, an APT Knowledge Graph (KG) enhanced by Large Language Models (LLMs), as a way to deal with the cybersecurity problems caused by Advanced Persistent Threats (APTs). The core of AEKG4APT lies in the combined application of LLMs, Cyber Threat Intelligence (CTI), and KG. The first part of the paper goes into great detail about how the AEKG4APT was constructed, including its ontology schema, data sources, and dataset features. There are also statistics on the AEKG4APT’s nodes, relationships, and key attributes. Secondly, it was shown how to utilize LLMs and public sandboxes for the collection and analysis of CTI Additionally, tests that compare traditional deep learning models to LLM methods show that LLM is both more efficient and more accurate at extracting information. Subsequently, the Decision Making Trial and Evaluation Laboratory - Interpretive Structural Modeling (DEMATEL-ISM) analytical method was introduced to identify and analyse the factors and their interrelationships within the AEKG4APT data, thereby revealing the key dependencies and influence paths within the data structure. Experiments were designed to demonstrate its applications in modeling, computing, and obtaining interpretable computational results on AEKG4APT. In addition, this paper also explores the dynamic expansion capabilities of AEKG4APT, including data expansion, schema expansion, and permanent maintenance strategies, to address the evolving APT threats. Finally, this paper summarizes the competitiveness and application value of AEKG4APT by comparing it with other CTI KGs and platforms in academia and industry, demonstrating its extensive application potential in the field of cybersecurity.

Details DOI

NeurIPS Conference 2025 Conference Paper

Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms

  • Philippe Wyder
  • Judah Goldfeder
  • Alexey Yermakov
  • Yue Zhao
  • Stefano Riva
  • Jan Williams
  • David Zoro
  • Amy Rude

Machine learning (ML) is transforming modeling and control in the physical, engineering, and biological sciences. However, rapid development has outpaced the creation of standardized, objective benchmarks—leading to weak baselines, reporting bias, and inconsistent evaluations across methods. This undermines reproducibility, misguides resource allocation, and obscures scientific progress. To address this, we propose a Common Task Framework (CTF) for scientific machine learning. The CTF features a curated set of datasets and task-specific metrics spanning forecasting, state reconstruction, and generalization under realistic constraints, including noise and limited data. Inspired by the success of CTFs in fields like natural language processing and computer vision, our framework provides a structured, rigorous foundation for head-to-head evaluation of diverse algorithms. As a first step, we benchmark methods on two canonical nonlinear systems: Kuramoto-Sivashinsky and Lorenz. These results illustrate the utility of the CTF in revealing method strengths, limitations, and suitability for specific classes of problems and diverse objectives. Next, we are launching a competition around a global real world sea surface temperature dataset with a true holdout dataset to foster community engagement. Our long-term vision is to replace ad hoc comparisons with standardized evaluations on hidden test sets that raise the bar for rigor and reproducibility in scientific ML.

PDF Details

JBHI Journal 2025 Journal Article

Data Knee Pads: A Lower Limb Motion Capture System Based on Heterogeneous Sensors

  • Yong Ding
  • Tianhang Nan
  • Fujia Wang
  • Yue Zhao
  • Xiaoyu Cui

Accurate lower limb motion capture is crucial for improving performance and user experience in fields such as motion analysis, rehabilitation training, and virtual reality. Traditional motion capture systems can only provide motion information, and often face issues such as occlusion or drift due to the limitations of sensor characteristics. For this purpose, we have designed a new type of data knee pad that integrates an Inertial Measurement Unit (IMU) and five liquid metal sensors. IMU provides basic motion data, while liquid metal sensors can provide information on joint bending and muscle activity. In order to extract effective information from sensor signals, we have developed an pose estimation model. The model first uses Fast Fourier Transform (FFT) to perform time-domain and frequency-domain analysis on the signal, in order to reveal hidden features in the signal. Next, inverse FFT and feature extraction are performed using the Transformer encoder to capture key motion features in the signal. Finally, we utilize a fully connected regression network to transform the extracted features into reconstruction of lower limb movements. Our system's lower limb pose estimation performance has been validated through a series of experiments, with an average tracking error of 1. 48° for the personalized model. In addition, the ability of the system to capture muscle activity signals was also verified through experiments. Our system has achieved high-precision measurement of knee joint bending angle while capturing muscle activity signals, which other existing technologies cannot achieve. This makes our system more widely applicable in fields such as motion detection and rehabilitation evaluation of muscle diseases.

Details DOI

NeurIPS Conference 2025 Conference Paper

DyFlow: Dynamic Workflow Framework for Agentic Reasoning

  • Yanbo Wang
  • Zixiang Xu
  • Yue Huang
  • Xiangqi Wang
  • Zirui Song
  • Lang Gao
  • Chenxi Wang
  • Robert Tang

Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed processes, which limits their adaptability across different tasks. While a few methods attempt automated workflow generation, they are often tied to specific datasets or query types and make limited use of intermediate feedback, reducing system robustness and reasoning depth. Moreover, their operations are typically predefined and inflexible. To address these limitations, we propose DyFlow, a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback, thereby enhancing cross-task generalization. DyFlow consists of two core components: a designer and an executor. The designer decomposes complex problems into a sequence of sub-goals defined by high-level objectives and dynamically plans the next steps based on intermediate outputs and feedback. These plans are then carried out by the executor, which executes each operation using dynamic operators with context-aware parameterization, enabling flexible and semantically grounded reasoning. We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation. Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains.

PDF Details

TMLR Journal 2025 Journal Article

LEGO-Learn: Label-Efficient Graph Open-Set Learning

  • Haoyan Xu
  • Kay Liu
  • Zhengtao Yao
  • Philip S. Yu
  • Mengyuan Li
  • Kaize Ding
  • Yue Zhao

How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify known, in-distribution (ID) classes while identifying and handling previously unseen classes during inference. It is critical for high-stakes, real-world applications where models frequently encounter unexpected data, including finance, security, and healthcare. However, current GOL methods assume access to a large number of labeled ID samples, which is unrealistic for large-scale graphs due to high annotation costs. In this paper, we propose LEGO-Learn (Label-Efficient Graph Open-set Learning), a novel framework that addresses open-set node classification on graphs within a given label budget by selecting the most informative ID nodes. LEGO-Learn employs a GNN-based filter to identify and exclude potential OOD nodes and then selects highly informative ID nodes for labeling using the K-Medoids algorithm. To prevent the filter from discarding valuable ID examples, we introduce a classifier that differentiates between the $C$ known ID classes and an additional class representing OOD nodes (hence, a $C+1$ classifier). This classifier utilizes a weighted cross-entropy loss to balance the removal of OOD nodes while retaining informative ID nodes. Experimental results on four real-world datasets demonstrate that LEGO-Learn significantly outperforms leading methods, achieving up to a $6.62\%$ improvement in ID classification accuracy and a $7.49\%$ increase in AUROC for OOD detection.

PDF Details

ICML Conference 2025 Conference Paper

Multivariate Conformal Selection

  • Tian Bai 0010
  • Yue Zhao
  • Xiang Yu
  • Archer Y. Yang

Selecting high-quality candidates from large datasets is critical in applications such as drug discovery, precision medicine, and alignment of large language models (LLMs). While Conformal Selection (CS) provides rigorous uncertainty quantification, it is limited to univariate responses and scalar criteria. To address this, we propose Multivariate Conformal Selection (mCS), a generalization of CS designed for multivariate response settings. Our method introduces regional monotonicity and employs multivariate nonconformity scores to construct conformal $p$-values, enabling finite-sample False Discovery Rate (FDR) control. We present two variants: $\texttt{mCS-dist}$, using distance-based scores, and $\texttt{mCS-learn}$, which learns optimal scores via differentiable optimization. Experiments on simulated and real-world datasets demonstrate that mCS significantly improves selection power while maintaining FDR control, establishing it as a robust framework for multivariate selection tasks.

Details

NeurIPS Conference 2025 Conference Paper

OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation

  • Xiaoan Zhu
  • Yue Zhao
  • Tianyang Hu
  • Jiaming Guo
  • Yulan Zeng
  • Renjing Pei
  • Fenglong Song
  • Huajun Feng

Dual-camera smartphones suffer from geometric and photometric inconsistencies during zoom transitions, primarily due to disparities in intrinsic/extrinsic parameters and divergent image processing pipelines between the two cameras. Existing interpolation methods struggle to effectively address this issue, constrained by the lack of ground-truth datasets and motion ambiguity in dynamic scenarios. To overcome these challenges, we propose OmniZoom, a universal plug-and-play paradigm for cross-device smooth zoom interpolation. Specifically, we present a novel cross-device virtual data generation method utilizing 3D Gaussian Splatting. This method tackles data scarcity by decoupling geometric features via spatial transition modeling and correcting photometric variations with dynamic color adaptation. It is further enhanced by cross-domain consistency learning for device-agnostic semantic alignment. Additionally, we introduce a plug-and-play 3D-TPR (3D Trajectory Progress Ratio Mapping) framework that surmounts 2D spatial limitations. As components of our framework, a texture-focus strategy is introduced for high-frequency detail preservation, incorporating mask penalty constraints to suppress interpolation artifacts. Our pipeline exhibits broad compatibility with diverse interpolation methods and achieves good performance across multiple public benchmarks. Real-world evaluations on various smartphone platforms also reveal significant quality improvements after fine-tuning on our synthetic data, which underscores the robustness and practical effectiveness of our approach for cross-device zoom applications.

PDF Details

ICRA Conference 2025 Conference Paper

Polyhedral Collision Detection via Vertex Enumeration

  • Andrew Cinar
  • Yue Zhao
  • Forrest Laine

Collision detection is a critical functionality for robotics. The degree to which objects collide cannot be represented as a continuously differentiable function for any shapes other than spheres. This paper proposes a framework for handling collision detection between polyhedral shapes. We frame the signed distance between two polyhedral bodies as the optimal value of a convex optimization, and consider constraining the signed distance in a bilevel optimization problem. To avoid relying on specialized bilevel solvers, our method exploits the fact that the signed distance is the minimal point of a convex region related to the two bodies. Our method enumerates the values obtained at all extreme points of this region and lists them as constraints in the higher-level problem. We compare our formulation to existing methods in terms of reliability and speed when solved using the same mixed complementarity problem solver. We demonstrate that our approach more reliably solves difficult collision detection problems with multiple obstacles than other methods, and is faster than existing methods in some cases.

Details

EAAI Journal 2025 Journal Article

Robust Bi-temporal cross-scene land cover map updating via curriculum-guided self-training and adversarial learning

  • Zhao Wang
  • Yue Zhao
  • Maoguo Gong
  • Hao Li
  • Gaogao Liu
  • Jianlong Tang

Bi-temporal land cover maps updating extends the traditional remote sensing image classification task to analyze land cover and land use (LC&LU) with unavailable ground truth and distribution shifts across the time scenarios. Difference-assisted knowledge transfer can alleviate the heavy annotation dependency on the target domain (newly collected image over the same region) to some extent. The inaccurate difference information obtained in an unsupervised manner often introduces a large number of mislabels for the training data on the target domain, while land cover transitions may contribute to the shortage of samples for specific ground categories on the target domain, i. e. , imbalance between categories. This paper proposes a collaborative curriculum self-training framework, which is considerably robust to inaccurate difference knowledge transferring, to learn a more generalized classifier for the target domain. Specifically, curriculum guided adversarial learning consists of three players, i. e. , curricula-classifier, curricula-generator, and discriminator, which aims at efficiently and reliably adapting to the negative effects of incorrect cross-domain mapping and the imbalanced long-tail distribution on self-training framework. Sample-level and task-level curriculum constraints are designed to collaboratively facilitate sample selection and task learning. The experimental results on four datasets (two pairs of bi-temporal images) show that the above method is able to perform robust learning and achieve remarkable classification performance. The code is released at https: //github. com/bling2beyond/Curricula-GAN.

Details DOI

JBHI Journal 2025 Journal Article

ToothAxis: Generalizable Tooth Axis Estimation Network from CBCT or IOS Models

  • Nan Bao
  • Qingyao Luo
  • Jiamin Wu
  • Zhiming Cui
  • Yue Zhao

Tooth axes, indicating the orientation of teeth, are crucial in orthodontics and dental implants. The precise and automated estimation of tooth axes in 3D dental models is of significant importance. In clinical settings, Cone-beam computed tomography (CBCT) images and intraoral scanning (IOS) models are the two primary forms of digital data, providing 3D volumetric and surface information of the oral cavity, respectively. However, the detection of tooth axes remains largely manual annotation due to the complexities associated with geometric definitions and the variations among different tooth types and individuals. In this paper, we propose a novel two-stage network, named ToothAxis, for tooth axis estimation using either CBCT or IOS models. Given that IOS models only capture the tooth crown surface and lack information about the tooth roots, we initially employ an implicit-function tooth completion module for 3D tooth completion in the first stage. Subsequently, with the 3D tooth models segmented from CBCT images or completed from IOS models, a point-wise offset-based module is proposed in the second stage to accurately estimate the tooth axes. This design aims to encode tooth orientation into a dense representation, which is better suited for sparse information regression tasks, such as tooth axis estimation. Additionally, we incorporate a class-specific feature attention module to integrate global context representation, thereby enhancing robustness in managing diverse tooth shapes. We evaluated ToothAxis on a dataset obtained from real-world dental clinics, comprising 529 tooth models with corresponding CBCT images and paired IOS models. Finally, the ToothAxis achieves angle errors of LA ( $2. 921^{\circ }$ ), PSA ( $4. 801^{\circ }$ ), and LSA ( $5. 074^{\circ }$ ) on tooth models extracted from CBCT images, and LA ( $5. 326^{\circ }$ ), PSA ( $6. 360^{\circ }$ ), and LSA ( $6. 520^{\circ }$ ) on partial crowns extracted from IOS models. Extensive evaluations, ablation studies, and comparative analyses demonstrate that our method achieves accurate tooth axis estimations and surpasses state-of-the-art approaches.

Details DOI

JBHI Journal 2024 Journal Article

A General DNA-Like Hybrid Symbiosis Framework: An EEG Cognitive Recognition Method

  • Hong Zeng
  • Yue Zhao
  • Fabio Babiloni
  • Ming Tao
  • Wanzeng Kong
  • Guojun Dai

In electroencephalogram (EEG) cognitive recognition research, the combined use of artificial neural networks (ANNs) and spiking neural networks (SNNs) plays an important role to realize different categories of recognition tasks. However, most of the existing studies focus on the unidirectional interaction between an ANN and a SNN, which may be overly dependent on the performance of ANNs or SNNs. Inspired by the symbiosis phenomenon in nature, in this study, we propose a general DNA-like Hybrid Symbiosis (DNA-HS) framework, which enables mutual learning between the ANN and the SNN generated by this ANN through parametric genetic algorithm and bidirectional interaction mechanism to enhance the optimization ability of the model parameters, resulting in a significant improvement of the performance of the DNA-HS framework in all aspects. By comparing with seven typical EEG cognitive recognition models, the performance of the seven hybrid network frameworks constructed using this method on different EEG-based cognitive recognition tasks are all improved to different degrees, verifying the effectiveness of the proposed method. This unified hybrid network framework similar to the DNA structure is expected to open up a new approach and form a new research paradigm for EEG-based cognitive recognition task.

Details DOI

JBHI Journal 2024 Journal Article

A Scalable Federated Learning Approach for Collaborative Smart Healthcare Systems With Intermittent Clients Using Medical Imaging

  • Farhan Ullah
  • Gautam Srivastava
  • Heng Xiao
  • Shamsher Ullah
  • Jerry Chun-Wei Lin
  • Yue Zhao

The healthcare industry is one of the most vulnerable to cybercrime and privacy violations because health data is very sensitive and spread out in many places. Recent confidentiality trends and a rising number of infringements in different sectors make it crucial to implement new methods that protect data privacy while maintaining accuracy and sustainability. Moreover, the intermittent nature of remote clients with imbalanced datasets poses a significant obstacle for decentralized healthcare systems. Federated learning (FL) is a decentralized and privacy-protecting approach to deep learning and machine learning models. In this article, we implement a scalable FL framework for interactive smart healthcare systems with intermittent clients using chest X-ray images. Remote hospitals may have imbalanced datasets with intermittent clients communicating with the FL global server. The data augmentation method is used to balance datasets for local model training. In practice, some clients may leave the training process while others join due to technical or connectivity issues. The proposed method is tested with five to eighteen clients and different testing data sizes to evaluate performance in various situations. The experiments show that the proposed FL approach produces competitive results when dealing with two distinct problems, such as intermittent clients and imbalanced data. These findings would encourage medical institutions to collaborate and use rich private data to quickly develop a powerful patient diagnostic model.

Details DOI

EAAI Journal 2024 Journal Article

Behavioral response of fish under ammonia nitrogen stress based on machine vision

  • Wenkai Xu
  • Chang Liu
  • Guangxu Wang
  • Yue Zhao
  • Jiaxuan Yu
  • Akhter Muhammad
  • Daoliang Li

The long-term accumulation of ammonia nitrogen in aquaculture seriously affects the life of fish and even causes large-scale death. Moreover, when the concentration of ammonia nitrogen starts to accumulate, it is a judgment standard to provide early warning through the changes in fish behavior to prevent excessive ammonia nitrogen in water. Therefore, this paper proposes a novel approach to monitoring water quality for aquaculture based on deep learning and three-dimensional movement trajectory. The improved YOLOv8 model was used as the object detection approach to obtain three-dimensional position information of fish by combining Kalman filter, Kuhn Munkres (KM) algorithm, and Kernelized Correlation Filters (KCF) algorithm. The proposed approach was evaluated in the recovery experiment of acute ammonia nitrogen stress of sturgeon, bass, and crucian. The experimental results show that the precision, recall, mAP@0. 5, and mAP@0. 5: 0. 95 of the improved YOLOv8 model are 0. 964, 0. 914, 0. 979, and 0. 602, respectively. In addition, the proposed three-dimensional positioning approach can qualitatively and quantitatively analyze the fish behavior in different stages and further explores the fish behavior changes through behavior trajectories, volumes of exercise, spatial distribution, and movement velocity. This research provides a new method and idea for studying the abnormal behavior of aquatic animals under ammonia nitrogen stress and has theoretical and practical significance.

Details DOI

YNICL Journal 2024 Journal Article

Cortical morphological alterations in adolescents with major depression and non-suicidal self-injury

  • Xiaonan Pang
  • Dongpeng Wu
  • Hongping Wang
  • Jiahua Zhang
  • Yue Yu
  • Yue Zhao
  • Qianqian Li
  • Liangping Ni

BACKGROUND: Non-suicidal self-injury (NSSI) involves repetitive self-harm without suicidal intent and is common among adolescents, often linked to major depressive disorder (MDD). NSSI can lead to physical harm, cognitive impairments, interpersonal issues, violent behavior, and increased risks of psychological disorders and suicide attempts later in life. METHODS: Voxel-based morphometry (VBM) and surface-based morphometry (SBM) were performed on 44 NSSI patients and 44 healthy controls (HCs). Differences in GMV, CT, and cortical complexity were compared using the two-sample t-tests and correlated with neuropsychological scales. RESULTS: NSSI patients exhibited significant GMV atrophy in multiple regions, including the left insula, left anterior cingulate cortex, left putamen, left middle frontal gyrus, and right superior frontal gyrus showing increased GMV in the cerebellum posterior lobe. NSSI patients had increased CT in multiple left hemisphere regions and decreased CT in the right middle frontal gyrus. Additionally, they exhibited reduced cortical complexity, including decreased SD in the right frontal gyrus, and lower GI in the left insula. There were no significant differences between the two groups in terms of fractal dimension (FD). NSSI patients showed negative correlation between the CT of the right middle frontal gyrus and the anger dimension of the BPAQ, as well as the SD of the right superior frontal gyrus and the hostility dimension of the BPAQ. CONCLUSION: NSSI patients have significant structural changes in the insular cortex, prefrontal cortex, precentral and postcentral gyrus, temporal lobe, putamen, and anterior cingulate cortex, offering a morphological perspective on the pathophysiology of NSSI in MDD.

Details DOI

ICLR Conference 2024 Conference Paper

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

  • Jinyi Hu
  • Yuan Yao 0013
  • Chongyi Wang
  • Shan Wang 0015
  • Yinxu Pan
  • Qianyu Chen
  • Tianyu Yu 0002
  • Hanghao Wu

Recently there has been a significant surge in multimodal learning in terms of both image-to-text and text-to-image generation. However, the success is typically limited to English, leaving other languages largely behind. Building a competitive counterpart in other languages is highly challenging due to the low-resource nature of non-English multimodal data (i.e., lack of large-scale, high-quality image-text data). In this work, we propose MPM, an effective training paradigm for training large multimodal models in low-resource languages. MPM demonstrates that Multilingual language models can Pivot zero-shot Multimodal learning across languages. Specifically, based on a strong multilingual large language model, multimodal models pretrained on English-only image-text data can well generalize to other languages in a (quasi)-zero-shot manner, even surpassing models trained on image-text data in native languages. Taking Chinese as a practice of MPM, we build large multimodal models VisCPM in image-to-text and text-to-image generation, which achieve state-of-the-art (open-source) performance in Chinese. To facilitate future research, we open-source codes and model weights at https://github.com/OpenBMB/VisCPM.

Details

ICLR Conference 2024 Conference Paper

LEAP: Liberate Sparse-View 3D Modeling from Camera Poses

  • Hanwen Jiang
  • Zhenyu Jiang 0002
  • Yue Zhao
  • Qi-Xing Huang

Are camera poses necessary for multi-view 3D modeling? Existing approaches predominantly assume access to accurate camera poses. While this assumption might hold for dense views, accurately estimating camera poses for sparse views is often elusive. Our analysis reveals that noisy estimated poses lead to degraded performance for existing sparse-view 3D modeling methods. To address this issue, we present LEAP, a novel pose-free approach, therefore challenging the prevailing notion that camera poses are indispensable. LEAP discards pose-based operations and learns geometric knowledge from data. LEAP is equipped with a neural volume, which is shared across scenes and is parameterized to encode geometry and texture priors. For each incoming scene, we update the neural volume by aggregating 2D image features in a feature-similarity-driven manner. The updated neural volume is decoded into the radiance field, enabling novel view synthesis from any viewpoint. On both object-centric and bounded scene-level datasets, we show that LEAP significantly outperforms prior methods when they employ predicted poses from state-of-the-art pose estimators. Notably, LEAP performs on par with prior approaches that use ground-truth poses while running $400\times$ faster than PixelNeRF. We show LEAP generalizes to novel object categories and scenes, and learns knowledge closely resembles epipolar geometry.

Details

NeurIPS Conference 2024 Conference Paper

Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence

  • Rakshit S. Trivedi
  • Akbir Khan
  • Jesse Clifton
  • Lewis Hammond
  • Edgar A. Duéñez-Guzmán
  • John P. Agapiou
  • Jayd Matyas
  • Sasha Vezhnevets

Multi-agent AI research promises a path to develop human-like and human-compatible intelligent technologies that complement the solipsistic view of other approaches, which mostly do not consider interactions between agents. Aiming to make progress in this direction, the Melting Pot contest 2023 focused on the problem of cooperation among interacting agents and challenged researchers to push the boundaries of multi-agent reinforcement learning (MARL) for mixed-motive games. The contest leveraged the Melting Pot environment suite to rigorously evaluate how well agents can adapt their cooperative skills to interact with novel partners in unforeseen situations. Unlike other reinforcement learning challenges, this challenge focused on social rather than environmental generalization. In particular, a population of agents performs well in Melting Pot when its component individuals are adept at finding ways to cooperate both with others in their population and with strangers. Thus Melting Pot measures cooperative intelligence. The contest attracted over 600 participants across 100+ teams globally and was a success on multiple fronts: (i) it contributed to our goal of pushing the frontiers of MARL towards building more cooperatively intelligent agents, evidenced by several submissions that outperformed established baselines; (ii) it attracted a diverse range of participants, from independent researchers to industry affiliates and academic labs, both with strong background and new interest in the area alike, broadening the field’s demographic and intellectual diversity; and (iii) analyzing the submitted agents provided important insights, highlighting areas for improvement in evaluating agents' cooperative intelligence. This paper summarizes the design aspects and results of the contest and explores the potential of Melting Pot as a benchmark for studying Cooperative AI. We further analyze the top solutions and conclude with a discussion on promising directions for future research.

PDF Details DOI

YNIMG Journal 2024 Journal Article

Meso-scale reorganization of local–global brain networks under mild sedation of propofol anesthesia

  • Kangli Dong
  • Lu Zhang
  • Yuming Zhong
  • Tao Xu
  • Yue Zhao
  • Siya Chen
  • Seedahmed S. Mahmoud
  • Qiang Fang

The fragmentation of the functional brain network has been identified through the functional connectivity (FC) analysis in studies investigating anesthesia-induced loss of consciousness (LOC). However, it remains unclear whether mild sedation of anesthesia can cause similar effects. This paper aims to explore the changes in local-global brain network topology during mild anesthesia, to better understand the macroscopic neural mechanism underlying anesthesia sedation. We analyzed high-density EEG from 20 participants undergoing mild and moderate sedation of propofol anesthesia. By employing a local-global brain parcellation in EEG source analysis, we established binary functional brain networks for each participant. Furthermore, we investigated the global-scale properties of brain networks by estimating global efficiency and modularity, and examined the changes in meso-scale properties of brain networks by quantifying the distribution of high-degree and high-betweenness hubs and their corresponding rich-club coefficients. It is evident from the results that the mild sedation of anesthesia does not cause a significant change in the global-scale properties of brain networks. However, network components centered on SomMot L show a significant decrease, while those centered on Default L, Vis L and Limbic L exhibit a significant increase during the transition from wakefulness to mild sedation (p<0.05). Compared to the baseline state, mild sedation almost doubled the number of high-degree hubs in Vis L, DorsAttn L, Limbic L, Cont L, and reduced by half the number of high-degree hubs in SomMot R, DorsAttn R, SalVentAttn R. Further, mild sedation almost doubled the number of high-betweenness hubs in Vis L, Vis R, Limbic R, Cont R, and reduced by half the number of high-betweenness hubs in SomMot L, SalVentAttn L, Default L, and SomMot R. Our results indicate that mild anesthesia cannot affect the global integration and segregation of brain networks, but influence meso-scale function for integrating different resting-state systems involved in various segregation processes. Our findings suggest that the meso-scale brain network reorganization, situated between global integration and local segregation, could reflect the autonomic compensation of the brain for drug effects. As a direct response and adjustment of the brain network system to drug administration, this spontaneous reorganization of the brain network aims at maintaining consciousness in the case of sedation.

Details DOI

NeurIPS Conference 2024 Conference Paper

MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities

  • Hao Dong
  • Yue Zhao
  • Eleni Chatzi
  • Olga Fink

Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios on image data. However, real-world applications are inherently multimodal, which makes it essential to leverage information from multiple modalities to enhance the efficacy of OOD detection. To establish a foundation for more realistic Multimodal OOD Detection, we introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes and varying modality combinations. We first evaluate existing unimodal OOD detection algorithms on MultiOOD, observing that the mere inclusion of additional modalities yields substantial improvements. This underscores the importance of utilizing multiple modalities for OOD detection. Based on the observation of Modality Prediction Discrepancy between in-distribution (ID) and OOD data, and its strong correlation with OOD performance, we propose the Agree-to-Disagree (A2D) algorithm to encourage such discrepancy during training. Moreover, we introduce a novel outlier synthesis method, NP-Mix, which explores broader feature spaces by leveraging the information from nearest neighbor classes and complements A2D to strengthen OOD detection performance. Extensive experiments on MultiOOD demonstrate that training with A2D and NP-Mix improves existing OOD detection algorithms by a large margin. To support accessibility and reproducibility, our source code and MultiOOD benchmark are available at https: //github. com/donghao51/MultiOOD.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Towards Reproducible, Automated, and Scalable Anomaly Detection

  • Yue Zhao

Anomaly detection (AD), often termed outlier detection, is a key machine learning (ML) task, aiming to identify uncommon yet crucial patterns in data. With the increasing complexity of the modern world, the applications of AD span wide—from NASA's spacecraft monitoring to early patient prioritization at University of Pittsburgh Medical Center. Technology giants like Google and Amazon also leverage AD for service disruption identification. Here, I will traverse my AD works with promising new directions, particularly emphasizing reproducible benchmarks (Part 1), automated algorithms (Part 2), and scalable systems (Part 3).

PDF Details DOI

AAAI Conference 2024 Conference Paper

UMA: Facilitating Backdoor Scanning via Unlearning-Based Model Ablation

  • Yue Zhao
  • Congyi Li
  • Kai Chen

Recent advances in backdoor attacks, like leveraging complex triggers or stealthy implanting techniques, have introduced new challenges in backdoor scanning, limiting the usability of Deep Neural Networks (DNNs) in various scenarios. In this paper, we propose Unlearning-based Model Ablation (UMA), a novel approach to facilitate backdoor scanning and defend against advanced backdoor attacks. UMA filters out backdoor-irrelevant features by ablating the inherent features of the target class within the model and subsequently reveals the backdoor through dynamic trigger optimization. We evaluate our method on 1700 models (700 benign and 1000 trojaned) with 6 model structures, 7 different backdoor attacks and 4 datasets. Our results demonstrate that the proposed methodology effectively detect these advanced backdoors. Specifically, our method can achieve 91% AUC-ROC and 86.6% detection accuracy on average, which outperforms the baselines, including Neural Cleanse, ABS, K-Arm and MNTD.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

ADGym: Design Choices for Deep Anomaly Detection

  • Minqi Jiang
  • Chaochuan Hou
  • Ao Zheng
  • Songqiao Han
  • Hailiang Huang
  • Qingsong Wen
  • Xiyang Hu
  • Yue Zhao

Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing. However, most of the current research tends to view deep AD algorithms as a whole, without dissecting the contributions of individual design choices like loss functions and network architectures. This view tends to diminish the value of preliminary steps like data preprocessing, as more attention is given to newly designed loss functions, network architectures, and learning paradigms. In this paper, we aim to bridge this gap by asking two key questions: (i) Which design choices in deep AD methods are crucial for detecting anomalies? (ii) How can we automatically select the optimal design choices for a given AD dataset, instead of relying on generic, pre-existing solutions? To address these questions, we introduce ADGym, a platform specifically crafted for comprehensive evaluation and automatic selection of AD design elements in deep methods. Our extensive experiments reveal that relying solely on existing leading methods is not sufficient. In contrast, models developed using ADGym significantly surpass current state-of-the-art techniques.

PDF Details

AAAI Conference 2023 Conference Paper

ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels

  • Yue Zhao
  • Guoqing Zheng
  • Subhabrata Mukherjee
  • Robert McCann
  • Ahmed Awadallah

Existing works on anomaly detection (AD) rely on clean labels from human annotators that are expensive to acquire in practice. In this work, we propose a method to leverage weak/noisy labels (e.g., risk scores generated by machine rules for detecting malware) that are cheaper to obtain for anomaly detection. Specifically, we propose ADMoE, the first framework for anomaly detection algorithms to learn from noisy labels. In a nutshell, ADMoE leverages mixture-of-experts (MoE) architecture to encourage specialized and scalable learning from multiple noisy sources. It captures the similarities among noisy labels by sharing most model parameters, while encouraging specialization by building "expert" sub-networks. To further juice out the signals from noisy labels, ADMoE uses them as input features to facilitate expert learning. Extensive results on eight datasets (including a proprietary enterprise security dataset) demonstrate the effectiveness of ADMoE, where it brings up to 34% performance improvement over not using it. Also, it outperforms a total of 13 leading baselines with equivalent network parameters and FLOPS. Notably, ADMoE is model-agnostic to enable any neural network-based detection methods to handle noisy labels, where we showcase its results on both multiple-layer perceptron (MLP) and the leading AD method DeepSAD.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

ADBench: Anomaly Detection Benchmark

  • Songqiao Han
  • Xiyang Hu
  • Hailiang Huang
  • Minqi Jiang
  • Yue Zhao

Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data? In this work, we answer these key questions by conducting (to our best knowledge) the most comprehensive anomaly detection benchmark with 30 algorithms on 57 benchmark datasets, named ADBench. Our extensive experiments (98, 436 in total) identify meaningful insights into the role of supervision and anomaly types, and unlock future directions for researchers in algorithm selection and design. With ADBench, researchers can easily conduct comprehensive and fair evaluations for newly proposed methods on the datasets (including our contributed ones from natural language and computer vision domains) against the existing baselines. To foster accessibility and reproducibility, we fully open-source ADBench and the corresponding results.

PDF Details

NeurIPS Conference 2022 Conference Paper

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

  • Kay Liu
  • Yingtong Dou
  • Yue Zhao
  • Xueying Ding
  • Xiyang Hu
  • Ruitong Zhang
  • Kaize Ding
  • Canyu Chen

Detecting which nodes in graphs are outliers is a relatively new machine learning task with numerous applications. Despite the proliferation of algorithms developed in recent years for this task, there has been no standard comprehensive setting for performance evaluation. Consequently, it has been difficult to understand which methods work well and when under a broad range of settings. To bridge this gap, we present—to the best of our knowledge—the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights. (1) We benchmark the outlier detection performance of 14 methods ranging from classical matrix factorization to the latest graph neural networks. (2) Using nine real datasets, our benchmark assesses how the different detection methods respond to two major types of synthetic outliers and separately to “organic” (real non-synthetic) outliers. (3) Using an existing random graph generation technique, we produce a family of synthetically generated datasets of different graph sizes that enable us to compare the running time and memory usage of the different outlier detection algorithms. Based on our experimental results, we discuss the pros and cons of existing graph outlier detection algorithms, and we highlight opportunities for future research. Importantly, our code is freely available and meant to be easily extendable: https: //github. com/pygod-team/pygod/tree/main/benchmark

PDF Details

NeurIPS Conference 2021 Conference Paper

Automatic Unsupervised Outlier Model Selection

  • Yue Zhao
  • Ryan Rossi
  • Leman Akoglu

Given an unsupervised outlier detection task on a new dataset, how can we automatically select a good outlier detection algorithm and its hyperparameter(s) (collectively called a model)? In this work, we tackle the unsupervised outlier model selection (UOMS) problem, and propose MetaOD, a principled, data-driven approach to UOMS based on meta-learning. The UOMS problem is notoriously challenging, as compared to model selection for classification and clustering, since (i) model evaluation is infeasible due to the lack of hold-out data with labels, and (ii) model comparison is infeasible due to the lack of a universal objective function. MetaOD capitalizes on the performances of a large body of detection models on historical outlier detection benchmark datasets, and carries over this prior experience to automatically select an effective model to be employed on a new dataset without any labels, model evaluations or model comparisons. To capture task similarity within our meta-learning framework, we introduce specialized meta-features that quantify outlying characteristics of a dataset. Extensive experiments show that selecting a model by MetaOD significantly outperforms no model selection (e. g. always using the same popular model or the ensemble of many) as well as other meta-learning techniques that we tailored for UOMS. Moreover upon (meta-)training, MetaOD is extremely efficient at test time; selecting from a large pool of 300+ models takes less than 1 second for a new task. We open-source MetaOD and our meta-learning database for practical use and to foster further research on the UOMS problem.

PDF Details

NeurIPS Conference 2021 Conference Paper

Revisiting Time Series Outlier Detection: Definitions and Benchmarks

  • Kwei-Herng Lai
  • Daochen Zha
  • Junjie Xu
  • Yue Zhao
  • Guanchu Wang
  • Xia Hu

Time series outlier detection has been extensively studied with many advanced algorithms proposed in the past decade. Despite these efforts, very few studies have investigated how we should benchmark the existing algorithms. In particular, using synthetic datasets for evaluation has become a common practice in the literature, and thus it is crucial to have a general synthetic criterion to benchmark algorithms. This is a non-trivial task because the existing synthetic methods are very different in different applications and the outlier definitions are often ambiguous. To bridge this gap, we propose a behavior-driven taxonomy for time series outliers and categorize outliers into point- and pattern-wise outliers with clear context definitions. Following the new taxonomy, we then present a general synthetic criterion and generate 35 synthetic datasets accordingly. We further identify 4 multivariate real-world datasets from different domains and benchmark 9 algorithms on the synthetic and the real-world datasets. Surprisingly, we observe that some classical algorithms could outperform many recent deep learning approaches. The datasets, pre-processing and synthetic scripts, and the algorithm implementations are made publicly available at https: //github. com/datamllab/tods/tree/benchmark

PDF Details

ICRA Conference 2021 Conference Paper

Stair Climbing Capability-Based Dimensional Synthesis for the Multi-legged Robot

  • Huayang Li
  • Chenkun Qi
  • Xianbao Chen
  • Liheng Mao
  • Yue Zhao
  • Feng Gao 0011

Staircase is a typical obstacle for the legged robot to overcome in buildings. This paper studies the stair climbing capability-based dimensional synthesis for a hexapod legged robot, i. e. , exploring how to determine the leg length and the longitudinal body length concerning the target staircase in the mechanical design stage. In climbing a staircase, leg-staircase interference is one of the predominant issues. The three possible interference cases are illustrated in detail with a 2-DOF (degree of freedom) leg mechanism and the staircase size, based on the predefined tripod gait sequence. The mathematical relationships between the leg length, longitudinal body length, and the target staircase size are derived. The leg length and the body length are finally determined with the target staircase size. The virtual simulations and prototype experiments verify the effectiveness of the dimensional synthesis for the hexapod robot.

Details

NeurIPS Conference 2021 Conference Paper

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development

  • Kexin Huang
  • Tianfan Fu
  • Wenhao Gao
  • Yue Zhao
  • Yusuf Roohani
  • Jure Leskovec
  • Connor Coley
  • Cao Xiao

Therapeutics machine learning is an emerging field with incredible opportunities for innovation and impact. However, advancement in this field requires the formulation of meaningful tasks and careful curation of datasets. Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics. To date, TDC includes 66 AI-ready datasets spread across 22 learning tasks and spanning the discovery and development of safe and effective medicines. TDC also provides an ecosystem of tools and community resources, including 33 data functions and diverse types of data splits, 23 strategies for systematic model evaluation, 17 molecule generation oracles, and 29 public leaderboards. All resources are integrated and accessible via an open Python library. We carry out extensive experiments on selected datasets, demonstrating that even the strongest algorithms fall short of solving key therapeutics challenges, including distributional shifts, multi-scale and multi-modal learning, and robust generalization to novel data points. We envision that TDC can facilitate algorithmic advances and considerably accelerate machine-learning model development, validation and transition into biomedical and clinical implementation. TDC is available at https: //tdcommons. ai.

PDF Details

AAAI Conference 2021 System Paper

TODS: An Automated Time Series Outlier Detection System

  • Kwei-Herng Lai
  • Daochen Zha
  • Guanchu Wang
  • Junjie Xu
  • Yue Zhao
  • Devesh Kumar
  • Yile Chen
  • Purav Zumkhawaka

We present TODS, an automated Time Series Outlier Detection System for research and industrial applications. TODS is a highly modular system that supports easy pipeline construction. The basic building block of TODS is primitive, which is an implementation of a function with hyperparameters. TODS currently supports 70 primitives, including data processing, time series processing, feature analysis, detection algorithms, and a reinforcement module. Users can freely construct a pipeline using these primitives and perform endto-end outlier detection with the constructed pipeline. TODS provides a Graphical User Interface (GUI), where users can flexibly design a pipeline with drag-and-drop. Moreover, a data-driven searcher is provided to automatically discover the most suitable pipelines given a dataset. TODS is released under Apache 2. 0 license at https: //github. com/datamllab/tods. A video is available on YouTube1.

PDF Details

AAAI Conference 2020 System Paper

Combining Machine Learning Models Using combo Library

  • Yue Zhao
  • Xuejian Wang
  • Cheng Cheng
  • Xueying Ding

Model combination, often regarded as a key sub-field of ensemble learning, has been widely used in both academic research and industry applications. To facilitate this process, we propose and implement an easy-to-use Python toolkit, combo, to aggregate models and scores under various scenarios, including classification, clustering, and anomaly detection. In a nutshell, combo provides a uni- fied and consistent way to combine both raw and pretrained models from popular machine learning libraries, e. g. , scikit-learn, XGBoost, and LightGBM. With accessibility and robustness in mind, combo is designed with detailed documentation, interactive examples, continuous integration, code coverage, and maintainability check; it can be installed easily through Python Package Index (PyPI) or https: //github. com/yzhao062/combo.

PDF Details

JMLR Journal 2019 Journal Article

PyOD: A Python Toolbox for Scalable Outlier Detection

  • Yue Zhao
  • Zain Nasrullah
  • Zheng Li

PyOD is an open-source Python toolbox for performing scalable outlier detection on multivariate data. Uniquely, it provides access to a wide range of outlier detection algorithms, including established outlier ensembles and more recent neural network-based approaches, under a single, well-documented API designed for use by both practitioners and researchers. With robustness and scalability in mind, best practices such as unit testing, continuous integration, code coverage, maintainability checks, interactive examples and parallelization are emphasized as core components in the toolbox's development. PyOD is compatible with both Python 2 and 3 and can be installed through Python Package Index (PyPI) or https://github.com/yzhao062/pyod. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2019. ( edit, beta )

PDF Details

NeurIPS Conference 2018 Conference Paper

Trajectory Convolution for Action Recognition

  • Yue Zhao
  • Yuanjun Xiong
  • Dahua Lin

How to leverage the temporal dimension is a key question in video analysis. Recent works suggest an efficient approach to video feature learning, i. e. , factorizing 3D convolutions into separate components respectively for spatial and temporal convolutions. The temporal convolution, however, comes with an implicit assumption – the feature maps across time steps are well aligned so that the features at the same locations can be aggregated. This assumption may be overly strong in practical applications, especially in action recognition where the motion serves as a crucial cue. In this work, we propose a new CNN architecture TrajectoryNet, which incorporates trajectory convolution, a new operation for integrating features along the temporal dimension, to replace the existing temporal convolution. This operation explicitly takes into account the changes in contents caused by deformation or motion, allowing the visual features to be aggregated along the the motion paths, trajectories. On two large-scale action recognition datasets, namely, Something-Something and Kinetics, the proposed network architecture achieves notable improvement over strong baselines.

PDF Details

YNIMG Journal 2017 Journal Article

In vivo detection of microstructural correlates of brain pathology in preclinical and early Alzheimer Disease with magnetic resonance imaging

  • Yue Zhao
  • Marcus E. Raichle
  • Jie Wen
  • Tammie L. Benzinger
  • Anne M. Fagan
  • Jason Hassenstab
  • Andrei G. Vlassenko
  • Jie Luo

Background Alzheimer disease (AD) affects at least 5 million individuals in the USA alone stimulating an intense search for disease prevention and treatment therapies as well as for diagnostic techniques allowing early identification of AD during a long pre-symptomatic period that can be used for the initiation of prevention trials of disease-modifying therapies in asymptomatic individuals. Methods Our approach to developing such techniques is based on the Gradient Echo Plural Contrast Imaging (GEPCI) technique that provides quantitative in vivo measurements of several brain-tissue-specific characteristics of the gradient echo MRI signal (GEPCI metrics) that depend on the integrity of brain tissue cellular structure. Preliminary data were obtained from 34 participants selected from the studies of aging and dementia at the Knight Alzheimer's Disease Research Center at Washington University in St. Louis. Cognitive status was operationalized with the Clinical Dementia Rating (CDR) scale. The participants, assessed as cognitively normal (CDR=0; n=23) or with mild AD dementia (CDR=0. 5 or 1; n=11) underwent GEPCI MRI, a collection of cognitive performance tests and CSF amyloid (Aβ) biomarker Aβ42. A subset of 19 participants also underwent PET PiB studies to assess their brain Aβ burden. According to the Aβ status, cognitively normal participants were divided into normal (Aβ negative; n=13) and preclinical (Aβ positive; n=10) groups. Results GEPCI quantitative measurements demonstrated significant differences between all the groups: normal and preclinical, normal and mild AD, and preclinical and mild AD. GEPCI quantitative metrics characterizing tissue cellular integrity in the hippocampus demonstrated much stronger correlations with psychometric tests than the hippocampal atrophy. Importantly, GEPCI-determined changes in the hippocampal tissue cellular integrity were detected even in the hippocampal areas not affected by the atrophy. Our studies also uncovered strong correlations between GEPCI brain tissue metrics and beta-amyloid (Aβ) burden defined by positron emission tomography (PET) – the current in vivo gold standard for detection of cortical Aβ, thus supporting GEPCI as a potential surrogate marker for Aβ imaging – a known biomarker of early AD. Remarkably, the data show significant correlations not only in the areas of high Aβ accumulation (e. g. precuneus) but also in some areas of medial temporal lobe (e. g. parahippocampal cortex), where Aβ accumulation is relatively low. Conclusion We have demonstrated that GEPCI provides a new approach for the in vivo evaluation of AD-related tissue pathology in the preclinical and early symptomatic stages of AD. Since MRI is a widely available technology, the GEPCI surrogate markers of AD pathology have a potential for improving the quality of AD diagnostic, and the evaluation of new disease-modifying therapies.

Details DOI

YNIMG Journal 2016 Journal Article

On the relationship between cellular and hemodynamic properties of the human brain cortex throughout adult lifespan

  • Yue Zhao
  • Jie Wen
  • Anne H. Cross
  • Dmitriy A. Yablonskiy

Establishing baseline MRI biomarkers for normal brain aging is significant and valuable for separating normal changes in the brain structure and function from different neurological diseases. In this paper for the first time we have simultaneously measured a variety of tissue specific contributions defining R2* relaxation of the gradient recalled echo (GRE) MRI signal in human brains of healthy adults (ages 22 to 74years) and related these measurements to tissue structural and functional properties. This was accomplished by separating tissue (R2 t ⁎) and extravascular BOLD contributions to the total tissue specific GRE MRI signal decay (R2⁎) using an advanced version of previously developed Gradient Echo Plural Contrast Imaging (GEPCI) approach and the acquisition and post-processing methods that allowed the minimization of artifacts related to macroscopic magnetic field inhomogeneities, and physiological fluctuations. Our data (20 healthy subjects) show that in most cortical regions R2 t ⁎ increases with age while tissue hemodynamic parameters, i. e. relative oxygen extraction fraction (OEFrel), deoxygenated cerebral blood volume (dCBV) and tissue concentration of deoxyhemoglobin (Cdeoxy) remain practically constant. We also found the important correlations characterizing the relationships between brain structural and hemodynamic properties in different brain regions. Specifically, thicker cortical regions have lower R2 t ⁎ and these regions have lower OEF. The comparison between GEPCI-derived tissue specific structural and functional metrics and literature information suggests that (a) regions in a brain characterized by higher R2 t ⁎ contain higher concentration of neurons with less developed cellular processes (dendrites, spines, etc.), (b) regions in a brain characterized by lower R2 t ⁎ represent regions with lower concentration of neurons but more developed cellular processes, and (c) the age-related increases in the cortical R2 t ⁎ mostly reflect the age-related increases in the cellular packing density. The baseline GEPCI-based biomarkers obtain herein could serve to help distinguish age-related changes in brain cellular and hemodynamic properties from changes which occur due to the neurodegenerative diseases.

Details DOI
v2026.09.13