赵洪科老师入职天津大学管理与经济学部！

Cube成立

2018年11月

Cube获得第一项研究资助（百度开放研究课题）！

获得研究资助

2020年1月

Cube获得研究生招生资格！

招收研究生

2020年7月

Cube首批硕士研究生毕业！

首批毕业生

2022年12月

吴李康老师入职天津大学管理与经济学部！

吴李康老师加入

2024年6月

Cube's 100th paper has been accepted/published!

Cube第100篇学术论文

2024年7月

吴李康老师课题《面向推荐领域的大模型复杂意图挖掘研究与应用》获批国家自然科学基金青年项目(C)

吴李康老师获批青基

2025年8月

吴李康老师开展首届硕士招生！

吴李康老师首届硕士招生

赵洪科老师开展首届博士招生！

Cube首届博士招生

赵洪科老师入选2026年天津市青年科技人才（第二层次）。

赵洪科老师入选天津市青年科技人才

2026年9月

赵洪科老师参加管理科学与工程学会年会，报告大模型驱动的生成式推荐服务智能体

赵洪科老师参加科技成果转化项目路演

A&DM-Cube师生参加各项国际学术会议

A&DM-Cube师生参加各项国内学术会议

赵洪科老师、吴李康老师参加联想与百度交流会

吴李康老师分享LLM4Rec

恭喜团队论文《From Chit-Chat to Conversion: Cost-Efficient Conversational Recommendation via Retrospective Learning and Isolated Reflection》被 Production and Operations Management (POM) 录用！Cube论文累计164篇，UTD24期刊论文增至3篇（2篇JOC、1篇POM）。

POM Accepted! Cube累计164篇论文，UTD24增至3篇

A&DM-Cube 2026夏季招生简章

《智能体：理论基础与应用实践》由何明、吕广奕、赵洪科、陈恩红、范建平著，现已出版。

AI Agent 著作《智能体：理论基础与应用实践》出版

恭喜团队的论文《Rational or Emotional? Next-item Recommendations in Virtual Games via Disentangling Players' Needs》被国际顶级期刊 INFORMS Journal on Computing (JOC) 录用。JOC 是 UTD 24 期刊之一。

JOC Accepted!

恭喜论文《Beyond Sequential Patterns: Rethinking Healthcare Predictions with Contextual Insights》被ACM TOIS接受，ACM TOIS（ACM Transactions on Information Systems）‌是信息检索领域的顶级期刊，由美国计算机学会（ACM）出版。论文《GCTN: Graph Competitive Transfer Network for Cross-Domain Multi-Behavior Prediction》被IEEE TKDE接受，IEEE TKDE(IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING)是数据科学与计算机领域的国际顶尖期刊。

TOIS/TKDE Accepted!

恭喜关钟论文《Attention Mechanisms Perspective: Exploring LLM Precessing of Graph-Structured Data》被ICML接收。ICML为中国计算机学会A类会议，全称为International Conference on Machine Learning。

ICML Accepted!

Two papers are accepted at AAAI 2025

Cube吴李康老师获批CAAI-联想蓝天科研基金资助！

A&DM-Cube招生简章

恭喜赵闯论文《Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment》被TSMC接收。TSMC为中国科学院一区top期刊IEEE Transactions on Systems, Man and Cybernetics: System。

TSMC Accepted!

恭喜项志晨论文《Performative Debias with Fair-exposure Optimization Driven by Strategic Agents in Recommender Systems》被TSMC接收。KDD全称为Knowledge Discovery and Data Mining，即知识发现与数据挖掘，是由ACM（Association for Computing Machinery，计算机协会）主办的国际性学术会议。该会议每年召开一次，旨在提供一个交流学术研究成果、展示最新技术、分享经验和思想的平台。KDD是国际上著名的数据挖掘和知识发现领域的重要会议，被认为是该领域中的顶级会议之一。

KDD Accepted!

Hao Wei achieves his Master's Degree in 2024.

Congratulations on Hao Wei's graduation!

Welcome Doctor Wu joining the Data&Algorithm Management Lab in 2024!

Welcome Likang Wu joing the team!

Haipeng Yuan achieves his Master's Degree in 2023.

Congratulations on Haipeng Yuan's graduation!

From Chit-Chat to Conversion: Cost-Efficient Conversational Recommendation via Retrospective Learning and Isolated Reflection

Spectral graph filter bank fusion for multimodal rumor cascade representation and detection

Learning–Optimization Interactive Framework for Evolutionary Multi-Objective Recommendation

Third-Party Risk Information Disclosure in Prosocial Crowdfunding: The Roles of Risk Level and Prosocial Orientation

Stock Time Series Prediction Correction Expert: A Knowledge-Guided Stable Multiple Large Language Models Enhancement Method

NaFreBformer: Natural gas pipeline leakage forecasting using Nyström approximation Transformer without frequency bias

Disentangling Relational Semantics in Graph Data to Summarize Entity Descriptions

AI-Driven Skill Keyword Suggestion for Multi-Round Interviews: A Graph-Based Topic Approach

Align Sequential Collaborative Signals and Text Semantics for Citation Recommendation: A Hybrid Perspective

Bridging the Gap in Cross-Domain Graph Anomaly Detection: Enhanced Source Utilization and Label Accuracy

Anomaly Detection in Industrial Internet of Things: A Graph Learning Approach with Spatio-temporal Interactions

Learn to Understanding: Knowledge Exemplification via Multi-Agent Cooperation for Science Question Answering

Beyond Popularity Bias in E-commerce: Aligning Collaborative Knowledge with Large Language Models via Causal Intervention for Robust Recommendations

基于知识增强的智能体复杂任务分解方法

How do crowdfunding models impact crowdfunding performance? The mediating role of backers’ ambiguity and herding effects

Improving Sentiment Analysis in Tourism through LLM-Enhanced Irony Detection

Enhancing Mathematical Reasoning through Autonomously Learning Knowledge

Rational or Emotional? Next-item Recommendations in Virtual Games via Disentangling Players' Needs

SimCDR: Preserving Intra-Domain Similarities of Users for Cross-Domain Recommendation

GDiffMAE: Guided Diffusion Enhanced Mask Graph AutoEncoder for Recommendation

GANPrompt: Improving LLM-Based Recommendations with GAN-Enhanced Diversity Prompts

Multi-Party Multi-Objective Optimization for Discrete Problems: A Case Study on Multi-Stakeholder Recommendation

MORA-LLM: Enhancing Multi-Objective Optimization Recommendation Algorithm by Integrating Large Language Models

Comparative Analysis of Algorithmic Approaches in Ensemble Learning: Bagging vs. Boosting

Multi-resolution leak detection based on shared expert MoE forecasting for natural gas pipelines

Collaborative Knowledge Fusion: A Novel Approach for Multi-task Recommender Systems via LLMs

Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learning

Cross-domain Transfer of Valence Preferences via a Meta-optimization Approach

How signal intensity of altruistic and strategic motivation affects crowdfunding performance? Matching among funders and platform types

Deeds Not Words: The Impact of Past Satisfaction and Behavior on Knowledge Cross-buying Intention on Online Course Platforms

Conflicts and optimization of multiple promotions combinations for merchants

Beyond Sequential Patterns: Rethinking Healthcare Predictions with Contextual Insights

GCTN: Graph Competitive Transfer Network for Cross-Domain Multi-Behavior Prediction

Multi-Objective Graph Contrastive Learning for Recommendation

Exploring the interpretability of vision GCN with a multi-method approach

Predicting scholar potential: a deep learning model on social capital features

Knowledge Enhanced Graph Contrastive Learning for Match Outcome Prediction

An efficient continuous control perspective for reinforcement-learning-based sequential recommendation

低碳神经网络算法：压缩和加速技术的发展与应用

Team formation in large organizations: A deep reinforcement learning approach

语言模型增强的引文网络连边因子挖掘

A Semi-supervised Reject Inference Framework with Hierarchical Heterogeneous Networks for Credit Scoring

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment

MOREM: An Evolutionary Multitasking Optimization Algorithm for Multi-Objective Recommendations

Supporting Your Idea Reasonably: A Knowledge-Aware Topic Reasoning Strategy for Citation Recommendation

第三方认证对亲社会众筹绩效的影响机制研究

A Multi-Population Based Evolutionary Algorithm for Many-Objective Recommendations

Does academic engagement with industry come at a cost for early career scientists? Evidence from high-tech enterprises’ Ph.D. funding programs

Free trial or no free trial: optimal operation of electronic physical product with positive and negative network effects

A Multi-aspect Neural Tensor Factorization Framework for Patent Litigation Prediction

Learning Relation-Enhanced Hierarchical Solver for Math Word Problems

Promoting Machine Abilities of Discovering and Utilizing Knowledge in a Unified Zero-shot Learning Paradigm

Caption matters: a new perspective for knowledge-based visual question answering

GTR: An Explainable Graph Topic-Aware Recommender for Scholarly Document

Enhancing Precision Drug Recommendations via In-depth Exploration of Motif Relationships

Cross-Domain Recommendation via Progressive Structural Alignment

An Ensemble Learning Approach with Gradient Resampling for Class-imbalance Problems

Multi-View Enhanced Zero-Shot Node Classification

SHGCN: Socially Enhanced Heterogeneous Graph Convolutional Network for Multi-Behavior Prediction

A General Tail Item Representation Enhancement Framework for Sequential Recommendation

What is Market Talking about? Market-oriented Prospect Analysis for Entrepreneur Fundraising

Learning the Explainable Semantic Relations via Unified Graph Topic-Disentangled Neural Networks

Forecasting movements of stock time series based on hidden state guided deep learning approach

A Community Division-Based Evolutionary Algorithm for Large-Scale Multi-Objective Recommendations

众筹项目筹资绩效的信息影响机制研究：基于Indiegogo平台证据

Lender Retention of Online Prosocial Lending: A Self-Determination Perspective

Personal or General? A Hybrid Strategy with Multi-factors for News Recommendation

A Sequence and Network Embedding Method for Bus Arrival Time Prediction using GPS Trajectory Data Only

Composing Like an Ancient Chinese Poet: Learn to Generate Rhythmic Chinese Poetry

Personalized Customer Lifetime Value Prediction in Online Games

Refined Analysis and a Hierarchical Multi-task Learning Approach for Loan Fraud Detection

CoEA: A Cooperative-Competitive Evolutionary Algorithm for Bidirectional Recommendations

The Effects of Person-Organization Fit on Lending Behaviors: Empirical Evidence from Kiva.org

Exploring the Effects of Social Capital on Crowdfunding Performance: A Holistic Analysis from the Empirical and Predictive Views

Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective

Toward Intelligent Financial Advisors for Identifying Potential Clients: A Multitask Perspective

Personalized Recommendation in P2P Lending Based on Risk-Return Management: A Multi-Objective Perspective

Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems

Rethinking the Development of Technology Enhanced Learning and the Role of Cognitive Computing

Dual-Stream Generative Adversarial Networks for Distributionally Robust Zero-Shot Learning

Can Cooperation Drive the Success of Suppliers in B2B Crowdsourcing Innovation Projects? A Large Scale Data Perspective

Voice of Charity: Prospecting the Donation Recurrence & Donor Retention in Crowdfunding

基于动静态表征的众筹协同预测方法

基于层级注意力机制的互联网用户信用评估框架

Product Supply Optimization for Crowdfunding Campaigns

An effectiveness analysis of altmetrics indices for different levels of artificial intelligence publications

A Structure-Enriched Neural Network for Network Embedding

基于跨域对抗学习的零样本分类

基于深度神经网络结构的互联网金融市场动态预测

实值优化问题的非对称负相关搜索算法

A Sequential Approach to Market State Modeling and Analysis in Online P2P Lending

Finding Potential Lenders in P2P Lending: A Hybrid Random Walk Approach

Illuminating Recommendation by Understanding the Explicit Item Relations

P2P Lending Survey: Platforms, Recent Advances and Prospects

用户在线购买预测:一种基于用户操作序列和选择模型的方法

网络小额贷款平台产品多维度分析与全局推荐

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation!

Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Lemon: Evidence-Risk-Aware Adaptive Organization for Long-Horizon LLM Agents

一种语言模型自适应策略融合训练方法及系统

Method of training prediction model, prediction method, electronic device and medium

跨域推荐和交互行为序列处理方法及相关设备

一种基于大语言模型的在线招聘推荐系统及方法

基于视觉组合关系学习的时尚服装智能搭配与推荐方法

一种基于多交互式注意力网络的点击率预测方法与装置

基于图学习和不确定行为建模的胜率预测系统及方法

跨域对抗神经网络模型及其训练方法,设备及存储介质

用于处理技能信息的方法、模型训练方法及装置

一种基于区块链技术的农业众筹平台

一种基于农村强社交关系的智能社交平台及社交方法

训练预测模型的方法、预测方法、装置、电子设备和介质

一种问答匹配注意力处理方法、计算机设备及存储介质

一种专利诉讼风险预测方法

基于动静态深度表征的协同预测方法

网络小额贷款中借款项目与出借人的双向匹配推荐方法

一种社区问答平台回答排序方法

一种基于用户行为区别建模的序列推荐方法

丰富结构信息的深度网络表征方法

一种跨领域情感分类方法和相关装置

一种中文文本的分类方法及系统

数据智能发展报告（2026）

LemonHarness Technical Report

人工智能政策对***影响分析

雄安新区综合数据平台(二期)项目建设咨询

IEEE Standard P3154 (Recommended Practice for the Application of Knowledge Graph for Talent Services)

Activities

Research network

Recent news

POM Accepted! Cube累计164篇论文，UTD24增至3篇

Milestone

Visitor’s Map

News and introduction

Activities

Research network

Recent news

POM Accepted! Cube累计164篇论文，UTD24增至3篇

Milestone

Visitor’s Map