Digital Commons Network^™

Seasonal Performance Of Mrms Qpe In Urban Hydrologic Modeling Using Epa-Swmm, Randall Kirk Bagwell

Theses and Dissertations

Accurate rainfall estimation is essential for effective hydrologic modeling, particularly in urban environments where infrastructure must withstand extreme precipitation. This study evaluates the EPA Storm Water Management Model (EPA-SWMM) using MRMS RadarOnly Quantitative Precipitation Estimation (QPE) 1-hour Accumulation as the primary rainfall input for a watershed in Little Rock, Arkansas. The region was selected due to its urban character and the limited availability of radar-based hydrologic studies in Arkansas. 21 storms were analyzed from 2022-2025: 10 in Winter, 7 in Spring, and 4 in Summer. Storms were selected due to their effect on flow. The model was calibrated using February …

Differential Photometric Analysis Of Exoplanet Candidates Toi-1362.01, Toi-2290.01, Toi-6010.01, And Toi-6324.01, Samantha Buck

Theses and Dissertations

To maximize the science return from the Transiting Exoplanet Survey Satellite (TESS), the TESS Follow-up Observing Program (TFOP) was created to network scientists and observatories to conduct follow-up observations of potential exoplanets. As members of TFOP-Subgroup 1, we observed four exoplanet candidates: TOI-1362.01, TOI-2290.01, TOI-6010.01, and TOI-6324.01 using the University of North Dakota Space Studies Observatory. The TOI observations were conducted from 31 October 2024 – 15 November, 2024 UTC. AstroImageJ software was used to perform differential photometry and, if a transit event was observed, determine orbital parameters and physical characteristics. Each of the target’s light curves was modeled and …

The Current Status And Challenges Of Korean Language Education In The Philippines: Insights From The Needs Of Non-Native Local Teachers, Kyoungsook Oh, Ma. Kristina Carla Rico, Sarah Jane D. Lipura

Korean Studies Department Faculty Publications

This study aims to identify developmental directions for Korean language education in the Philippines by analyzing the educational realities and needs of Filipino Korean language teachers working locally. Although Korean language education has been expanding in schools, universities, and various institutions, the system lacks institutional foundations and research on teachers. To address this, an online survey was conducted with 21 teachers across the Philippines, and 19 valid responses were analyzed. The respondents were employed in universities, King Sejong Institutes, vocational training centers, religious institutions, and private language schools. Many teachers had limited Korean proficiency, insufficient academic background or training experience, …

More Than Peyote: Trauma, Healing, And The Politics Of Indigenous Cultural Survival In The Age Of Psychedelic Colonialism, Christine Diindiisi Mccleave

Indigenous Studies

This dissertation examines the intersection of peyote religion, historical trauma, and the emergent psychedelic movement through a critical Indigenous lens. Centering peyote as both a sacred medicine and a symbolic flashpoint, the study highlights how contemporary psychedelic policy, practice, and commercialization perpetuate settler-colonial paradigms and threaten Indigenous cultural survival. While mainstream narratives frame psychedelics as tools for healing, this research emphasizes how such framing often obscures deeper histories of dispossession, cultural appropriation, and epistemic violence. Using a mixed-methods approach, including 50 anonymous survey responses, 13 qualitative interviews, and a 6-person focus group, this study amplifies the voices of tribal citizens …

Developing A LingíT Cultural Learning Theory, Eldri Waid Westmoreland

Indigenous Studies

This dissertation develops a Lingít cultural learning theory grounded in ancestral knowledge, cultural values, and intergenerational oral histories. Rooted in Indigenous methodologies and guided by Grounded Theory, the study explores how Lingít ways of knowing, centered on relationships, reciprocity, and respect can inform and transform educational practices for all learners and teachers. Through open-ended interviews and archival transcripts, participants recalled their earliest learning experiences using sensory memory and each identified emotional safety as a key factor for engagement in the learning process. These narratives revealed four foundational themes: processes, patterns, principles, and purposes of learning. The resulting theory honors the …

Environmental Identities Of College Students Reveal Potential Conflicts And Common Ground For Wildlife Conservation, Richard Von Furstenberg, Lincoln R. Larson, M. Nils Peterson, Kangjae Jerry Lee, Victoria R. Vayer, Kathryn Stevenson, Stacy A.C. Nelson, Jeremy Bruskotter, Adam A. Ahlers, Christine Anhalt-Depies, Taniya Bethke, Chris Chizinski, Brian Clark, Kiley M.D. Fryman, Ashley A. Dayer, Benjamin Ghasemi, Larry Gigliotti, Alan Graefe, Samuel J. Keith, Matt Kelly, Gerard Kyle, Elizabeth Metcalf, Wayde Morse, Mark D. Needham, Neelam C. Poudyal, Michael Quartuch, Shari L. Rodriguez, Chelsie Romulo, Ryan L. Sharp, William Siemer, Matt Springer

Michigan Tech Publications

“Conservationist” and “environmentalist” are two prominent environmental social identities often perceived as conflicting, particularly on wedge issues like hunting. While these groups may hold differing philosophies, their beliefs could overlap, revealing opportunities for collaboration in conservation. We examined environmental identities among U.S. college students across 22 states (n = 17,203) from 2018 to 2020, assessing identity, wildlife values, and positions on polarizing issues. Students were classified into four groups: conservationists (8 %), environmentalists (9 %), pluralists (59 %) who expressed both identities, and eco-agnostics (24 %) who expressed neither. Environmentalists, the most diverse group demographically, exhibited mutualistic wildlife value orientations, …

Awareness And Usability Of Community And Facility-Based Health Sector Client Feedback Mechanism In Tanzania Public Health System. A Mixed Methods Study, James Kengia, Pius Kagoma, Ally Kinyaga, Helga Mutasingwa, Simon Debere, Robert Smith, Marcos Mzeru, Rashid Mbunda, Claud Kumalija, Paschal Ruggajo

Internal Medicine, East Africa

Background Client feedback systems are increasingly becoming important in person-centered health care. The systems provide opportunities to the public to interact with the health care providers and policymakers, present their concerns related to the performance of the health care system in order to improve the quality, equity, and responsiveness in the provision of services, hence increase social accountability. This study aimed to assess the situation of client feedback systems in Tanzania, focusing on the awareness and usability of existing facility- and community-based feedback platforms from the client’s perspective.

Methods The study employed a concurrent mixed-method design using both quantitative and …

Clinical Phenotypes Of Motor Neurone Disease In A Kenyan Hospital-Based Population, Effie Nailah Kamadi, Jasmit Shah, Juzar Hooker, Thomas Jenkins, Dilraj Sokhi

Internal Medicine, East Africa

Background: Motor neurone disease (MND) presentation is globally heterogenous and data on the clinical phenotype in Sub-Saharan Africa (SSA) is scarce. We sought to address this by describing the profile of MND patients in a Kenyan hospital-based population.

Methods: The medical charts of all adult MND patients assessed in the facility between January 2010 and December 2023 were retrospectively reviewed. The biographical data and clinical features of these patients were captured from their electronic and manual health records and statistical analysis performed.

Results: In total, 160 patients had their data analyzed. The male to female ratio was 1.76:1. The median …

Striatal Compartment And White Matter Alterations In Focal Dystonia Subtypes: An Mri Study, Artur José Marques Paulo, Jeff L. Waugh, Anderson M. Winkler, Joselisa Peres Queiroz De Paiva, Danilo Donizete De Faria, Vanderci Borges, Sonia De Azevedo Silva, Henrique Ballalai De Ferraz, Patricia De Carvalho Aguiar

Human Genetics Publications

Introduction: Dystonia is a movement disorder marked by involuntary muscle contractions that cause abnormal postures or repetitive movements. The striatum plays a key role in motor control and is central to dystonia pathophysiology. Recent advances in diffusion MRI enable in vivo parcellation of the striatum into matrix- and striosome-like compartments, associated with sensorimotor and limbic functions. We aimed to assess structural brain differences between focal dystonia patients and healthy controls (HC) using T1-weighted and diffusion MRI, and to explore subtype-specific alterations in striatal compartments.

Methods: We analyzed 3T MRI data from 91 participants: 29 with upper limb dystonia (ULD), 25 …

The Music & The Movement: Race, Rhythm, And Social Justice, Renee Nicole Allen -- Associate Professor Of Law

Vanderbilt Journal of Entertainment & Technology Law

From Billie Holiday’s “Strange Fruit” to Public Enemy’s “Fight the Power” to J. Cole’s “Be Free,” music has played a vital role in energizing social justice movements and elevating the legal and social issues facing Black people. An examination into the legal, historical, and social contexts for the music created during ten key movements in Black history reveals the role of lyrics and rhythm. Through the lens of music, ten movements—Freedom, Lynching, the Great Migration, Civil Rights, Black Power, Black Feminism, Police Brutality, Mass Incarceration, Black Love, and Black Lives Matter—demonstrate that Black music is more than entertainment. It is …

Island-Based Evolutionary Computation With Diverse Surrogates And Adaptive Knowledge Transfer For High-Dimensional Data-Driven Optimization, Xianrong Zhang, Yuejiao Gong, Zhiguang Cao, Jun Zhang

Research Collection School Of Computing and Information Systems

In recent years, there has been a growing interest in data-driven evolutionary algorithms (DDEAs) employing surrogate models to approximate the objective functions with limited data. However, current DDEAs are primarily designed for lower-dimensional problems and their performance drops significantly when applied to large-scale optimization problems (LSOPs). To address the challenge, this paper proposes an offline DDEA named DSKT-DDEA. DSKT-DDEA leverages multiple islands that utilize different data to establish diverse surrogate models, fostering diverse subpopulations and mitigating the risk of premature convergence. In the intra-island optimization phase, a semi-supervised learning method is devised to fine-tune the surrogates. It not only facilitates …

Digital Communications Between Firms And Investors: Impact Of Explanatory Responses On Investor Engagement In Online Financial Q&A, Runyu Wang, Zili Zhang, Keng Siau, Ziqiong Zhang

Research Collection School Of Computing and Information Systems

The emerging trend of digital communications between firms and investors through online question-and-answer (Q&A) platforms is recognized as a vital strategy for managing investor relations, contributing to enhanced market efficiency and information transparency through increased information exchange. Potential investors can seek responses from firm managers to address their information needs, thereby mitigating market uncertainties. To provide foundational insights, we conduct a survey of investors to assess their awareness, usage, and perceptions of firm-investor Q&A platforms. In the subsequent empirical study, we specifically focus on the substance of managers’ responses, which are primarily aimed at clarifying firm events or information. In …

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun

Research Collection School Of Computing and Information Systems

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversaryspecified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM1 , the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of …

A Learning‑Augmented Dynamic Programming Approach For Orienteering Problem With Time Windows, Guansheng Peng, Lining Xing, Fuyan Song Ma, Aldy Gunawan, Aldy Gunawan

Research Collection School Of Computing and Information Systems

Recent years have witnessed a surge of interest in solving combinatorial optimization problems (COPs) using machine learning techniques. Motivated by this trend, we propose a learning-augmented exact approach for tackling an NP-hard COP, the Orienteering Problem with Time Windows, which aims to maximize the total score collected by visiting a subset of vertices in a graph within their time windows. Traditional exact algorithms rely heavily on domain expertise and meticulous design, making it hard to achieve further improvements. By leveraging deep learning models to learn effective relaxations of problem restrictions from data, our approach enables significant performance gains in an …

Sopo: Text-To-Motion Generation Using Semi-Online Preference Optimization, Xiaofeng Tan, Hongsong Wang, Xin Geng, Pan Zhou

Research Collection School Of Computing and Information Systems

Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fine-tuning text-to-motion models to consistently favor highquality, human-preferred motions—a critical yet largely unexplored problem. In this work, we theoretically investigate the DPO under both online and offline settings, and reveal their respective limitation: overfitting in offline DPO, and biased sampling in online DPO. Building on our theoretical insights, we introduce Semi-online Preference Optimization (SoPo), a DPO-based method for training text-to-motion models using “semi-online” data pair, consisting of unpreferred motion from online distribution and preferred motion in …

Hybrid-Balance Gflownet For Solving Vehicle Routing Problems, Ni Zhang, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Existing GFlowNet-based methods for vehicle routing problems (VRPs) typically employ Trajectory Balance (TB) to achieve global optimization but often neglect important aspects of local optimization. While Detailed Balance (DB) addresses local optimization more effectively, it alone falls short in solving VRPs, which inherently require holistic trajectory optimization. To address these limitations, we introduce the Hybrid-Balance GFlowNet (HBG) framework, which uniquely integrates TB and DB in a principled and adaptive manner by aligning their intrinsically complementary strengths. Additionally, we propose a specialized inference strategy for depot-centric scenarios like the Capacitated Vehicle Routing Problem (CVRP), leveraging the depot node's greater flexibility in …

Uniteformer: Unifying Node And Edge Modalities In Transformers For Vehicle Routing Problem, Dian Meng, Zhiguang Cao, Jie Gao, Yaoxin Wu, Yaqing Hou

Research Collection School Of Computing and Information Systems

Neural solvers for the Vehicle Routing Problem (VRP) have typically relied on either node or edge inputs, limiting their flexibility and generalization in real-world scenarios. We propose UniteFormer, a unified neural solver that supports node-only, edge-only, and hybrid input types through a single model trained via joint edge-node modalities. UniteFormer introduces: (1) a mixed encoder that integrates graph convolutional networks and attention mechanisms to collaboratively process node and edge features, capturing cross-modal interactions between them; and (2) a parallel decoder enhanced with query mapping and a feed-forward layer for improved representation. The model is trained with REINFORCE by randomly sampling …

Large Language Models As End-To-End Combinatorial Optimization Solvers, Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models (LLMs) have shown promise in automating CO problem solving, existing approaches rely on intermediate steps such as code generation or solver invocation, limiting their generality and accessibility. This paper introduces a novel framework that empowers LLMs to serve as end-to-end CO solvers by directly mapping natural language problem descriptions to solutions. We propose a two-stage training strategy: supervised fine-tuning (SFT) imparts LLMs with solution generation patterns from domain-specific solvers, while a feasibility-and-optimality-aware reinforcement learning …

Learning Memory-Enhanced Improvement Heuristics For Flexible Job Shop Scheduling, Jiaqi Wang, Zhiguang Cao, Peng Zhao, Rui Cao, Yubin Xiao, Yuan Jiang, You Zhou

Research Collection School Of Computing and Information Systems

The rise of smart manufacturing under Industry 4.0 introduces mass customization and dynamic production, demanding more advanced and flexible scheduling techniques. The flexible job-shop scheduling problem (FJSP) has attracted significant attention due to its complex constraints and strong alignment with real-world production scenarios. Current deep reinforcement learning (DRL)-based approaches to FJSP predominantly employ constructive methods. While effective, they often fall short of reaching (near-)optimal solutions. In contrast, improvement-based methods iteratively explore the neighborhood of initial solutions and are more effective in approaching optimality. However, the flexible machine allocation in FJSP poses significant challenges to the application of this framework, including …

Registration Is A Powerful Rotation-Invariance Learner For 3d Anomaly Detection, Yuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang, Haoxin Yang, Yongwei Nie, Shengfeng He

Research Collection School Of Computing and Information Systems

3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability. However, current memory bank-based methods often suffer from inconsistent feature transformations and limited discriminative capacity, particularly in capturing local geometric details and achieving rotation invariance. These limitations become more pronounced when registration fails, leading to unreliable detection results. We argue that point-cloud registration plays an essential role not only in aligning geometric structures but also in guiding feature extraction toward rotation-invariant and locally discriminative representations. To this end, we propose a registration-induced, rotation-invariant feature extraction framework that integrates the objectives …

Jury-And-Judge Chain-Of-Thought For Uncovering Toxic Data In 3d Visual Grounding, Kaixiang Huang, Qifeng Zhang, Jin Wang, Jingru Yang, Yang Zhou, Huan Yu, Guodong Lu, Shengfeng He

Research Collection School Of Computing and Information Systems

3D Visual Grounding (3DVG) faces persistent challenges due to coarse scene-level observations and logically inconsistent annotations, which introduce ambiguities that compromise data quality and hinder effective model supervision. To address these challenges, we introduce Refer-Judge, a novel framework that harnesses the reasoning capabilities of Multimodal Large Language Models (MLLMs) to identify and mitigate toxic data. At the core of Refer-Judge is a Jury-and-Judge Chain-of-Thought paradigm, inspired by the deliberative process of the judicial system. This framework targets the root causes of annotation noise: jurors collaboratively assess 3DVG samples from diverse perspectives, providing structured, multi-faceted evaluations. Judges then consolidate these insights …

Misodice: Multi-Agent Imitation From Mixed-Quality Demonstrations, The Viet Bui, Tien Mai, Hong Thanh Nguyen

Research Collection School Of Computing and Information Systems

We study offline imitation learning (IL) in cooperative multi-agent settings, where demonstrations have unlabeled mixed quality - containing both expert and suboptimal trajectories. Our proposed solution is structured in two stages: trajectory labeling and multi-agent imitation learning, designed jointly to enable effective learning from heterogeneous, unlabeled data. In the first stage, we combine advances in large language models and preference-based reinforcement learning to construct a progressive labeling pipeline that distinguishes expert-quality trajectories. In the second stage, we introduce MisoDICE, a novel multi-agent IL algorithm that leverages these labels to learn robust policies while addressing the computational complexity of large joint …

Iostom: Offline Imitation Learning From Observations Via State Transition Occupancy Matching, Quang Anh Pham, Brahmanage Janaka Chathuranga Thilakarathna, Tien Mai, Akshat Kumar

Research Collection School Of Computing and Information Systems

Offline Learning from Observations (LfO) focuses on enabling agents to imitate expert behavior using datasets that contain only expert state trajectories and separate transition data with suboptimal actions. This setting is both practical and critical in real-world scenarios where direct environment interaction or access to expert action labels is costly, risky, or infeasible. Most existing LfO methods attempt to solve this problem through state or state-action occupancy matching. They typically rely on pretraining a discriminator to differentiate between expert and non-expert states, which could introduce errors and instability—especially when the discriminator is poorly trained. While recent discriminator-free methods have emerged, …

Rising From Ashes: Generalized Federated Learning Via Dynamic Parameter Reset, Jiahao Wu, Ming Hu, Yanxin Yang, Xiaofei Xie, Zekai Chen, Chenyu Song, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Federated Learning (FL) is promising for privacy-preserving collaborative model training, it suffers from low inference performance due to heterogeneous client data. Due to heterogeneous data across clients, FL training easily learns client-specific overfitting features. Existing FL methods adopt coarsegrained averaging, which can easily cause the global model to get stuck in local optima, leading to poor generalization. Specifically, this paper presents a novel FL framework, FedPhoenix, to address this issue. It stochastically resets partial parameters in each round to destroy some features of the global model, guiding FL training to learn multiple generalized features for inference rather than specific …

Cssa-Fusion: Channel Selective And Spatial Alignment Infrared-Visible Image Fusion, Zhen Li, Zhi Zeng, Zhongrui Xiao, Ming Wen, Zhiyuan Zhang, Yibin Tian

Research Collection School Of Computing and Information Systems

Infrared-visible image fusion aims to integrate complementary information from two modalities to generate images with enriched semantic content. However, existing methods often neglect two critical aspects: the design of a local–global feature enhancement architecture and spatial alignment. To address these challenges, we propose Channel Selective and Spatial Alignment Fusion (CSSA-Fusion), a novel framework composed of two synergistic modules. The first is a selective channel and redundancy suppression module, which introduces a dual-branch selective channel attention mechanism to jointly capture local saliency and global channel importance for enhanced feature representation, and an informativeness–redundancy separation strategy to suppress redundant information while preserving …

When Less Language Is More: Language-Reasoning Disentanglement Makes Llms Better Multilingual Reasoners, Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu

Research Collection School Of Computing and Information Systems

Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration from cognitive neuroscience, which suggests that human reasoning functions largely independently of language processing, we hypothesize that LLMs similarly encode reasoning and language as separable components that can be disentangled to enhance multilingual reasoning. To evaluate this, we perform a causal intervention by ablating language-specific representations at inference time. Experiments on 10 open-weight LLMs spanning 11 typologically diverse languages show that this language-specific ablation consistently boosts multilingual reasoning performance. Layer-wise analyses further confirm that language and reasoning representations can be effectively …

Instance-Level Video Depth In Groups Beyond Occlusions, Yuan Liang, Yang Zhou, Ziming Sun, Tianyi Xiang, Guiqing Li, Shengfeng He

Research Collection School Of Computing and Information Systems

Depth estimation in dynamic, multi-object scenes remains a major challenge, especially under severe occlusions. Existing monocular models, including foundation models, struggle with instance-wise depth consistency due to their reliance on global regression. We tackle this problem from two key aspects: data and methodology. First, we introduce the Group Instance Depth (GID) dataset, the first large-scale video depth dataset with instance-level annotations, featuring 101,500 frames from real-world activity scenes. GID bridges the gap between synthetic and real-world depth data by providing high-fidelity depth supervision for multi-object interactions. Second, we propose InstanceDepth, the first occlusion-aware depth estimation framework for multi-object environments. Our …

Robust Hallucination Detection In Llms Via Adaptive Token Selection, Mengjia Niu, Hamed Haddadi, Guansong Pang

Research Collection School Of Computing and Information Systems

Hallucinations in large language models (LLMs) pose significant safety concerns that impede their broader deployment. Recent research in hallucination detection has demonstrated that LLMs’ internal representations contain truthfulness hints, which can be harnessed for detector training. However, the performance of these detectors is heavily dependent on the internal representations of predetermined tokens, fluctuating considerably when working on free-form generations with varying lengths and sparse distributions of hallucinated entities. To address this, we propose HaMI, a novel approach that enables robust detection of hallucinations through adaptive selection and learning of critical tokens that are most indicative of hallucinations. We achieve this …

Semi‑Supervised Graph Anomaly Detection Via Robust Homophily Learning, Guoguo Ai, Hezhe Qiao, Hui Yan, Guansong Pang

Research Collection School Of Computing and Information Systems

Current semi-supervised graph anomaly detection (GAD) methods utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. These methods posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the entire normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of …