Digital Commons Network^™

The Miseducation Of Model Minorities: The Gospel Of ‘Schoolvation’ And The Myth Of The Schooled Society, Justin Kh Tse

Research Collection College of Integrative Studies

The ‘model minority’, the phenomenon of some ‘minority’ communities (or some members within them) achieving social and economic advancement despite encountering the difficulties of assimilating into a mainstream society, is often described as a myth, especially as one of the central problematics in Asian American studies. Usually, the modern use of the word myth is pejorative: the model minority in this sense refers to a false empirical description of some minorities and should be quantitatively disaggregated and qualitatively debunked. In this article, I want to explore the model minority as another kind of myth, in the classical sense of mythos, …

A New City For A New Era: Xiong'an As Showcase Of China's Evolving Urban Ideology, Andrew Stokols

Research Collection College of Integrative Studies

Cities have long been expressions of political ideology in China and elsewhere. During China’s rapid urbanization over the past few decades, “new areas” became popular strategies to promote urban growth, following the success of Shenzhen, widely regarded as China’s first special economic zone. Today under Xi, Xiong’an New Area has become the latest “new area of national significance.” But unlike previous new areas in China, Xiong’an has become wedded to a distinct vision of the urban in Xi Jinping’s China, one in which the excesses of reform-era urbanization are controlled through new forms of affordable housing and finance, new ecological …

Investigating The Thixotropy Of Fresh Struvite Cement-Based Composite: Insights On Mechanisms Of The Pastes’ Thixotropic Behavior, Ugochukwu Ewuzie, Abdulkareem O. Yusuf, Damilola Daramola, Monday Uchenna Okoronkwo

Chemical and Biochemical Engineering Faculty Research & Creative Works

Struvite (ST) recovered during wastewater treatment has been sparsely applied in cement-based composites. This study systematically evaluated the thixotropic behavior of cement-struvite (CST) pastes, a mix of 5–20 % ST by mass of cement, and proposed the interaction mechanisms leading to the pastes' thixotropy. The hysteresis loop area was used to establish the pastes' thixotropy and investigate its relationship with increased ST content, temperature, and yield stress. In the thixotropic behavior model used, the equilibrium shear stress was employed to examine the CST pastes' irreversible change; the characteristic time of deflocculation was used to study the flocs destruction process; and …

Gallium-Containing Bioactive Glasses: Their Influence On Ion Release And The Bioactivity Of Resulting Glass Polyalkenoate Cements, Lana Margaret Placek, Danielle Lee Perry, Mark Robert Towler, Anthony William Wren

Chemical and Biochemical Engineering Faculty Research & Creative Works

A series of glasses (0.48SiO2 − [0.40-x]ZnO − 0.12CaO-xGa2O3, x = 0, 0.8, 0.16) was developed to formulate a series of Ga-containing glass polyalkenoate cements (GPCs). The solubility of GPCs was tested using DI water, and it was found that the sample containing the highest mol% of Ga, LGa-2, had the most Ga ion release. The GPCs were incubated in SBF, and SEM/EDS analysis revealed that the at% of P increased, while the at% of Si decreased, highlighting the CaP precipitation on the GPC surface. The at% of Ga also decreased, reinforcing the Ga release from the GPC. Cellular testing …

The Diabetes Prevention Program And Its Outcomes Study: Niddk's Journey Into The Prevention Of Type 2 Diabetes And Its Public Health Impact, Jill P Crandall, Dana Dabelea, William C Knowler, David M Nathan, Marinella Temprosa, Dpp Research Group

Children’s Nutrition Research Center Staff Publications

The current-day epidemic of type 2 diabetes, largely driven by increased adiposity and reduced physical activity in the setting of genetic susceptibility, is a major public health challenge. The National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) presciently proposed the Diabetes Prevention Program (DPP), a multicenter randomized clinical trial, designed by investigators in conjunction with NIDDK staff and initiated in 1996. The primary goal of DPP was to determine whether an intensive lifestyle intervention (ILS) or metformin in comparison with placebo would reduce the development of diabetes in a high-risk population with prediabetes. After mean 2.8 years, ILS …

An Incentive Mechanism For Privacy Preserved Data Trading With Verifiable Data Disturbance, Man Zhang, Xinghua Li, Bin Luo, Yanbing Ren, Yinbin Miao, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

To motivate data owners’ (DOs’) trading willingness, the existing incentive mechanisms allow DOs to independently disturb data following data consumer's (DC’s) availability requirement. However, they cannot motivate DOs’ honest disturbance, which is attributed to DOs’ independent disturbance without any supervision. Thus, we implement an incentive mechanism for privacy preserved data trading with verifiable data disturbance where an honest-but-curious disturbance generator (DG) is additionally introduced to supervise DOs’ local disturbance and assist disturbance verification between DOs and DC. Specifically, DG generates the disturbance strategies and secretly distributes to DOs following private information retrieval, guaranteeing DOs's local disturbance's privacy and verifiability with …

Splenic Function Post Radiation Therapy In Childhood Cancer Survivors, Joy M. Fulbright, Kyla Alsman, Ashley K. Sherman, Kris Laurence, Becky Lowry

Manuscripts, Articles, Book Chapters and Other Papers

Study evaluated splenic function in childhood cancer survivors (CCS) who had received radiation to the spleen utilizing pRBC PIT (vesiculated erythrocytes) count compared to a non-radiated control group. Those exposed to < 20 Gy of radiation had PIT counts not significantly different from the control group. There was trend for higher pRBC PIT count in those exposed to higher doses of radiation.

Willa Cather’S Uneven Ground: Guest Editor's Introduction, Emily J. Rau

University of Nebraska-Lincoln Libraries: Faculty Publications

Guest editor's introduction to the summer 2025 issue of Western American Literature, a special issue on resettling Willa Cather’s West.

Leveraging Chorionic Villus Biopsies For The Derivation Of Patient-Specific Trophoblast Stem Cells., Kaela Varberg, Ayelen Moreno-Irusta, Allynson Novoa, Brynne Musser, Joseph M. Varberg, Jeremy P. Goering, Irfan Saadi, Khursheed Iqbal, Hiroaki Okae, Takahiro Arima, John Williams, Margareta D. Pisarska, Michael J. Soares

Manuscripts, Articles, Book Chapters and Other Papers

Human trophoblast stem (TS) cells are informative in vitro models for the generation and testing of biologically meaningful hypotheses. The goal of this project was to derive patient-specific TS cell lines from clinically available chorionic villus biopsies. Cell outgrowths were captured from human chorionic villus tissue specimens cultured in modified human TS cell medium. Cell colonies emerged early during the culture and cell lines were established and passaged for several generations. Karyotypes of the newly established chorionic villus-derived trophoblast stem (TS^CV) cell lines were determined and compared to initial genetic diagnoses from freshly isolated chorionic villi. Phenotypes of …

Call It When You See It: Major League Soccer Organization And Pediatric Hospital Team Up For Anti-Bullying Program., Ram Chettiar

Manuscripts, Articles, Book Chapters and Other Papers

Bullying remains a widespread social issue in the United States (US). Those who bully, are bullied, or witness bullying may experience negative emotional and physical consequences.1 To address the gap in accessible youth bullying interventions, Children's Mercy Kansas City partnered with Sporting Kansas City to develop Red Card KC, a bullying awareness program focusing on the impact of bystanders in bullying situations. The program is delivered to school and community partners through interactive assemblies educating youth on recognizing bullying, managing bullying situations, and standing up against bullying. Red Card KC has also partnered with schools to recognize and celebrate students …

Letter Of Concern From The Association Of Academic Chairs Of Emergency Medicine Regarding Acgme Proposed Changes., Richard J. Hamilton, Lance B. Becker, Richard E. Wolfe, D Adam Algren, Thomas Arnold, Michael Baumann, Ross P. Berkeley, Terrell S. Caffery, Chad M. Cannon, Theodore J. Corbin, Michael E. Chansky, Harinder S. Dhindsa, Charles L. Emerman, David A. Farcy, Chris Fox, Michael A. Gibbs, Christopher S. Goode, Steven Andy Godwin, Dietrich Jehle, David Johnson, Samuel M. Keim, Babak Khazaeni, Barry J. Knapp, Clint Hawthorne, John D. Hoyle, Michael Christopher Kurz, Evan Leibner, Robert Mcnamara, Robert F. Mccormack, Edward A. Michelson, Chadwick Miller, Ashley Norse, Andrew Nugent, Brian J. O'Neil, David T. Overton, Edward A. Panacek, William F. Paolo, Denis R. Pauzé, Amanda L. Perez, Ralph J. Riviello, Scott W. Rodi, Peter S. Pang, Juan A. Gonzalez Sanchez, David Seaberg, Adam Schwartz, Stephen A. Shiver, David P. Sklar, Ben C. Smith, Jeffrey R. Stowell, Marc D. Squillante, J Jeremy Thomas, Terry Vanden Hoek, Gregory A. Volturo, E Lea Walters, Thomas E. Wyatt, Donald M. Yealy

Manuscripts, Articles, Book Chapters and Other Papers

This letter, signed by over 50 academic chairs of emergency medicine, urges the ACGME to reconsider a proposed mandate requiring all emergency medicine residency programs to adopt a four-year training model. The authors argue that current three-year programs are supported by data demonstrating equivalent educational and clinical outcomes compared to four-year formats. They criticize the flawed survey methodology underpinning the proposal, note the loss of milestone-based training flexibility, and highlight the lack of added scholarly or clinical value in the fourth year. The letter also outlines negative consequences for fellowship participation, workforce development, trainee debt, and diversity. The signatories advocate …

Characterizing Long Covid Symptoms During Early Childhood., Rachel S. Gross, Tanayott Thaweethai, Amy L. Salisbury, Lawrence C. Kleinman, Sindhu Mohandas, Kyung E. Rhee, Jessica N. Snowden, Kelan G. Tantisira, David Warburton, John C. Wood, Patricia A. Kinser, Joshua D. Milner, Erika B. Rosenzweig, Katherine Irby, Valerie J. Flaherman, Elizabeth W. Karlson, Lori B. Chibnik, Deepti B. Pant, Aparna Krishnamoorthy, Richard Gallagher, Michelle F. Lamendola-Essel, Denise C. Hasson, Stuart D. Katz, Shonna Yin, Benard P. Dreyer, Frank Blancero, Megan Carmilani, K Coombs, Megan L. Fitzgerald, Rebecca J. Letts, Aimee K. Peddie, Judy L. Aschner, Andrew M. Atz, Dithi Banerjee, Amanda Bogie, Hulya Bukulmez, Katharine Clouser, Lesley A. Cottrell, Kelly Cowan, Viren A. D'Sa, Allen Dozor, Amy J. Elliott, E Vincent S. Faustino, Alexander G. Fiks, Sunanda Gaur, Maria L. Gennaro, Stewart Gordon, Uzma N. Hasan, Christina M. Hester, Alexander Hogan, Daniel S. Hsia, David C. Kaelber, Jessica S. Kosut, Sankaran Krishnan, Russell J. Mcculloh, Ian C. Michelow, Sheila M. Nolan, Carlos R. Oliveira, Lynn M. Olson, Wilson D. Pace, Paul Palumbo, Hengameh Raissy, Andy Reyes, Judith L. Ross, Juan C. Salazar, Rangaraj Selvarangan, Cheryl R. Stein, Michelle D. Stevenson, Ronald J. Teufel, Alan Werzberger, John M. Westfall, Kathleen Zani, William T. Zempsky, Emily Zimmerman, Marie-Abele C. Bind, James Chan, Zoe Guan, Richard E. Morse, Harrison T. Reeder, Torri D. Metz, Jane W. Newburger, Dongngan T. Truong, Andrea S. Foulkes, Melissa S. Stockwell, Recover-Pediatrics Consortium, Recover-Pediatrics Group Authors

Manuscripts, Articles, Book Chapters and Other Papers

IMPORTANCE: Recent studies have identified characteristic symptom patterns of long COVID (LC) in adults and children older than 5 years. However, LC remains poorly characterized in early childhood. This knowledge gap limits efforts to identify, care for, and prevent LC in this vulnerable population.

OBJECTIVES: To identify symptoms that had the greatest difference in frequency comparing children with a history of SARS-CoV-2 infection to those without, to identify differences in the types of symptoms by age group (infants/toddlers [0-2 years] vs preschool-aged children [3-5 years]), and to derive an index that can be used in research studies to identify young …

Afit Librarian Newsletter : Check It Out (Third Quarter 2025), D'Azzo Research Library, Air Force Institute Of Technology

AFIT Library Knowledge Base

In this issue:

• Interview with a Featured Library Advocate, Dr. Michael Miller, ENV.
• 25th Anniversary of the joint library operations with AFRL

Research On The Capacity Development Of National Science And Technology Intelligence System, Hui Li, Shu Chen, Xiao Tan

Journal of Scientific Information Research

[Purpose/significance] The unique form and systematic characteristics of great power competition, such as system-establishment and whole of society confrontation, multi-domain and multi-depth high-tech containment and counter-containment, and multi-means and multi-element mixed deterrence, determine that national scientific and technological intelligence must have considerable systemic capabilities to match and follow up.

[Method/process] This article focuses on scientific and technological intelligence institutions within the traditional system, defines the connotation of national scientific and technological intelligence system capabilities, constructs a six-dimensional capability cognition model of ""institutional improvement capability-system coordination capability-resource guarantee capability-technological innovation capability-intelligence shaping capability-safe operation capability"", and expounds its main contents.

[Result/conclusion] …

Research On The Evolutionary Game Of Users' Digital Reading Trace Sharing From Perspective Of Privacy Protection, Jing Liu, Jingyu Ji, Chengzhi Liu, Liyan Chang

Journal of Scientific Information Research

[Purpose/significance] Under the perspective of privacy protection, exploring the sharing of users' digital reading traces is of great significance for creating a healthy and orderly digital reading environment and promoting the high-quality development of national reading.

[Method/process] A tripartite evolutionary game model of users, digital reading platforms and the government is constructed to reveal the dynamic evolution process and stable strategy of each subject's strategy selection through mathematical derivation, and numerical simulation is used to verify the accuracy of the model.

[Result/conclusion] The study shows that the strategy choices of users, digital reading platforms and the government are highly coupled, …

The Formation Mechanism Of Irrational Online Comments From The Perspective Of Dual Systems Theory, Xuefen Wang, Lei Guo, Liyan Chang, Zejiao Jiang

Journal of Scientific Information Research

[Purpose/significance] To explore the internal formation mechanism of unplanned irrational online comments is of great significance to promote the governance of cyberspace and the control of user behavior.

[Method/process] Based on the dual-system theory, the study constructed a model for the formation mechanism of irrational online comments, and revealed how online disinhibition and the spiral of silence affect individual internal states to stimulate irrational comments through empirical analysis.

[Result/conclusion] Research reveals that: compared to mild irrational comments, aggressive irrational comments are more likely to be unplanned behaviors, the cognitive-emotional preoccupation with online comments is the main driving factor for irrational …

Research On Technology Opportunity Identification By Integrating Technology Attribute Analysis And Competitive Environment Scanning —— A Case Study Of Industrial Robots, Daobin Gao

Journal of Scientific Information Research

[Purpose/significance] Placing technology opportunity identification in the perspective of technology attribute analysis and competitive environment scanning provides intelligence support for enterprises to select technology opportunities and formulate technology competitive strategies in complex and changing market competition environments.

[Method/process] Using patents as the data source, first, the BERTopic model is used to explore potential technical topics, Secondly, starting from the technical attributes, and from both global and local perspectives, we propose indicators of technical importance and technical attention, and use their cross screening to select candidate sets of technical opportunities, Finally, a market competition intensity index that takes into account market …

Culture Bears The Way, While Technology Facilitates Action: Research Of The Adoption Willingness Of Aigc In Academic Writing Among Young Scholars, Jiangfeng Liu, Zihui Wang, Zhiwei Hu, Lei Pei

Journal of Scientific Information Research

[Purpose/significance] Clarifying the influencing factors of young scholars' willingness to use AIGC and its path of action,then making effective enhancement strategies,would help to further expand the application of AIGC in academic writing.

[Method/process] This paper combs through the studies on AIGC information behavior, and identifies TOE(Technology-Organization-Envifonment，TOE) theory and research life cycle theory as the base theory. Semi-structured interviews were conducted for procedural grounded theory coding. Then, a questionnaire survey and qualitative comparative analysis using fuzzy sets were conducted to obtain the influencing factors grouping path.

[Result/conclusion] Five factors, induding content quality, system quality, perceived risk, expectation confirmation, and group norms, …

Unm Pathology, Pathfinder Summer 2025, Unm Department Of Pathology

Newsletters

No abstract provided.

Artificial Intelligence And Humanoid Robotics: Bioethical Implications Of Replacing Human Agency In Healthcare And Beyond, Sara Feizyab, Gabriele Bonetti, Maria Chiara Medori, Cecilia Micheletti, Immacolata De Luca, Kevin Donato, Jan Miertuš, Mehmet Sait Dundar, Miroslava Vráblová, Gary Henehan, Richard Brown, Robert Marks, Stanislav Miertus, Lorenzo Lorusso, Gianluca Martino Tartaglia, Munis Dundar, Sandro Michelini, Stephen Thaddeus Connelly, Ariola Bacu, Tommaso Beccari, Ornela Gordani, Xhilda Dhamo, Eglantina Kalluci, Dominika Vešelényiová, Iveta Dirgová Luptáková, Jiri Pospíchal, Matteo Bertelli

Research Outputs: 2025-Present

The integration of advanced artificial intelligence (AI) and humanoid robotics into healthcare represents a critical evolution in biotechnology with profound societal implications. This review explores the bioethical implications of these technologies, and their potential to displace human agency in life-critical decisions. It adopts an interdisciplinary approach encompassing ethics, law, and technology. The review examines how innovations in AI and robotics might shift autonomy from humans to machines, and addresses the accountability challenges inherent in such transitions. We synthesize discussions on the ethical management of AI and robotics, underscoring the importance of maintaining human oversight and integrating ethical standards in technology …

Araştırma Alanında Toplumsal Cinsiyet Eşitliği Üzerine Bir Değerlendirme: Avrupa Birliği Cinsiyet Eşitliği Stratejileri Ve Araştırma Çerçeve Programları, Guldan Kalem

Research Outputs: 2025-Present

This paper addresses the issue of gender equality in science, research, and innovation in the context of the European Union's Equality Strategies and Research and Innovation Framework Programs. The study aims to provide predictions for the future in this area through the analysis of priorities and actions outlined in the European Union’s gender equality strategies and research and innovation framework programs to promote gender equality in the field of research. Document review and analysis methods were used as research methods. The analysis of the documents shows that the European Union priorities in the area of gender inequality in research are …

An Exponential Cone Integer Programming And Piece-Wise Linear Approximation Approach For 0-1 Fractional Programming, Hoang Giang Pham, Thuy Anh Ta, Tien Mai

Research Collection School Of Computing and Information Systems

We study a class of binary fractional programs commonly encountered in important application domains such as assortment optimization and facility location. These problems are known to be NP-hard to approximate within any constant factor, and existing solution approaches typically rely on mixed-integer linear programming or second-order cone programming reformulations. These methods often utilize linearization techniques (e.g., big-M or McCormick inequalities), which can result in weak continuous relaxations. In this work, we propose a novel approach based on an exponential cone reformulation combined with piecewise linear approximation. This allows the problem to be solved efficiently using standard cutting-plane or branch-and-cut procedures. …

Position: Trustworthy Ai Agents Require The Integration Of Large Language Models And Formal Methods, Yedi Zhang, Yufan Cai, Xinyue Zuo, Xiaokun Luan, Kailong Wang, Zhe Hou, Yifan Zhang, Zhiyuan Wei, Meng Sun, Jun Sun, Jing Sun, Jin Song Dong

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have emerged as a transformative AI paradigm, profoundly influencing broad aspects of daily life. Despite their remarkable performance, LLMs exhibit a fundamental limitation: hallucination—the tendency to produce misleading outputs that appear plausible. This inherent unreliability poses significant risks, particularly in high-stakes domains where trustworthiness is essential. On the other hand, Formal Methods (FMs), which share foundations with symbolic AI, provide mathematically rigorous techniques for modeling, specifying, reasoning, and verifying the correctness of systems. These methods have been widely employed in mission-critical domains such as aerospace, defense, and cybersecurity. However, the broader adoption of FMs remains constrained …

Llmscan: Causal Scan For Llm Misbehavior Detection, Mengdi Zhang, Kai Kiat Goh, Peixin Zhang, Jun Sun, Lin Xin Rose, Hongyu Zhang

Research Collection School Of Computing and Information Systems

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While existing approaches target specific issues such as harmful responses, this work introduces LLMSCAN, an innovative LLM monitoring technique based on causality analysis, offering a comprehensive solution. LLMSCAN systematically monitors the inner workings of an LLM through the lens of causal inference, operating on the premise that the LLM’s ‘brain’ behaves differently when generating harmful or untruthful responses. By analyzing …

Hps: Hard Preference Sampling For Human Preference Alignment, Xiandong Zou, Wanyu Lin, Yuchen Li, Pan Zhou

Research Collection School Of Computing and Information Systems

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on PlackettLuce (PL) and Bradley-Terry (BT) models have shown promise, they face challenges such as poor handling of harmful content, inefficient use of dispreferred responses, and, specifically for PL, high computational costs. To address these issues, we propose Hard Preference Sampling (HPS), a novel framework for robust and efficient human preference alignment. HPS introduces a training loss that prioritizes the most preferred response while rejecting all dispreferred and harmful ones. It emphasizes “hard” dispreferred responses — those …

Sigfinger: A Subtle And Interactive Gnn Fingerprinting Scheme Via Spatial Structure Inference Perturbation, Ju Jia, Renjie Li, Cong Wu, Siqi Ma, Lina Wang, Robert H. Deng

Research Collection School Of Computing and Information Systems

There have been significant improvements in intellectual property (IP) protection for deep learning models trained on euclidean data. However, the complex and irregular graph-structured data in non-euclidean space poses a huge challenge to the IP protection of graph neural networks (GNNs). To address this issue, we propose a subtle and interactive GNN fingerprinting scheme through spatial structure inference perturbation, which captures the stable coordination patterns of fingerprint to guarantee the reliability of copyright verification. Specifically, the data augmentation based on adaptive graph diffusion is first exploited to generate more samples, which enables the exploration of fingerprint information from coarse to …

Unambiguous Granularity Distillation For Asymmetric Image Retrieval, Hongrui Zhang, Yi Xie, Haoquan Zhang, Cheng Xu, Xuandi Luo, Donglei Chen, Xuemiao Xu, Huaidong Zhang, Pheng Ann Heng, Shengfeng He

Research Collection School Of Computing and Information Systems

Previous asymmetric image retrieval methods based on knowledge distillation have primarily focused on aligning the global features of two networks to transfer global semantic information from the gallery network to the query network. However, these methods often fail to effectively transfer local semantic information, limiting the fine-grained alignment of feature representation spaces between the two networks. To overcome this limitation, we propose a novel approach called Layered-Granularity Localized Distillation (GranDist). GranDist constructs layered feature representations that balance the richness of contextual information with the granularity of local features. As we progress through the layers, the contextual information becomes more detailed, …

Llm-Based Multi-Agent Systems For Software Engineering: Literature Review, Vision And The Road Ahead, Junda He, Christoph Treude, David Lo

Research Collection School Of Computing and Information Systems

Integrating Large Language Models (LLMs) into autonomous agents marks a significant shift in the research landscape by offering cognitive abilities that are competitive with human planning and reasoning. This paper explores the transformative potential of integrating Large Language Models into Multi-Agent (LMA) systems for addressing complex challenges in software engineering (SE). By leveraging the collaborative and specialized abilities of multiple agents, LMA systems enable autonomous problem-solving, improve robustness, and provide scalable solutions for managing the complexity of real-world software projects. In this paper, we conduct a systematic review of recent primary studies to map the current landscape of LMA applications …

Diversity Optimization For Travelling Salesman Problem Via Deep Reinforcement Learning, Qi Li, Zhiguang Cao, Yining Ma, Yaoxin Wu, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution. To discover diverse yet high-quality solutions for Multi-Solution TSP (MSTSP), we propose a novel deep reinforcement learning based neural solver, which is primarily featured by an encoder-decoder structured policy. Concretely, on the one hand, a Relativization Filter (RF) is designed to enhance the robustness of the encoder to affine transformations of the instances, so as to potentially improve the quality of the found solutions. On the other hand, a Multi-Attentive Adaptive Active Search (MA3S) is tailored to allow the decoders to strike a …

An Efficient Diffusion-Based Non-Autoregressive Solver For Traveling Salesman Problem, Mingzhao Wang, You Zhou, Zhiguang Cao, Yubin Xiao, Xuan Wu, Wei Pang, Yuan Jiang, Hui Yang, Peng Zhao, Yuanshu Li

Research Collection School Of Computing and Information Systems

Recent advances in neural models have shown considerable promise in solving Traveling Salesman Problems (TSPs) without relying on much hand-crafted engineering. However, while non-autoregressive (NAR) approaches benefit from faster inference through parallelism, they typically deliver solutions of inferior quality compared to autoregressive ones. To enhance the solution quality while maintaining fast inference, we propose DEITSP, a diffusion model with efficient iterations tailored for TSP that operates in a NAR manner. Firstly, we introduce a one-step diffusion model that integrates the controlled discrete noise addition process with self-consistency enhancement, enabling optimal solution prediction through simultaneous denoising of multiple solutions. Secondly, we …