IEEE TKDE

4,462 papers1,251 directions
IEEE Transactions on Knowledge and Data Engineering (TKDE) is a peer-reviewed journal active since 1993 that focuses on the intersection of data engineering, knowledge discovery, and machine learning. The venue publishes research concerning the design, implementation, and management of data-intensive systems and the extraction of knowledge from large-scale datasets. Its scope encompasses foundational data structures, scalable algorithms, and the application of artificial intelligence to complex data environments. The journal is characterized by a focus on graph-based machine learning and data stream processing. Key research directions represented in the venue include the development of dynamic node embeddings for time-evolving networks, memory-efficient graph processing, and scalable graph centrality analysis. Additionally, the venue features work on data quality, specifically regarding joint imputation and classification for incomplete datasets and modeling the signals inherent in missing data. Prolific contributors to the journal include researchers such as Xiaofang Zhou, Feiping Nie, Wenjie Zhang, and Xuelong Li. Recent publications indicate an integration of emerging technologies into the journal's core focus areas. This includes the application of Large Language Models (LLMs) for misinformation detection, bug detection in database engines, and managing scientific complexity through automated peer review systems. Other topics include spatial graph-based foundation models for urban representation and safety mechanisms within graph machine learning. By bridging the gap between database management and advanced analytics, the journal serves as a venue for research on the scalability and reliability of data-driven AI systems.

Papers by Year

2026 285
2025 479
2024 601
2023 834
2022 460
2021 314
2020 232
2019 209
2018 185
2017 183
2016 177
2015 181
2014 146
2013 132
2012 100
2011 90
2010 95
2009 72
2008 66
2007 50
2006 58
2005 56
2004 50
2003 41
2002 26
2001 27
2000 13
1999 22
1998 14
1997 16
1996 18
1995 9
1994 14
1993 7
1992 5
1991 5
1990 2
1989 3

Top Research Directions

Research directions most represented by papers from this venue.

Self Supervised Regularization for Sparse Recommender Systems 26
Dynamic Preference Modeling in Interactive Systems 25
Over-Smoothing in Graph Neural Networks 19
Cross-Task Generalization in Graph Neural Networks 11
Transparent Reasoning for Personalized Recommendation 11
Meta Path Learning in Heterogeneous Networks 10
Overcoming the Homophily Assumption in Graph Neural Networks 10
Adapting Homogeneous Graph Learning to Heterogeneous Structures 9
Scaling Graph Learning to Massive Networks 9
Knowledge Retention in Continual Deep Learning 9
Fusing Exogenous Context into Spatio-Temporal Neural Networks 8
Multimodal Feature Fusion for Recommender Systems 8
Learning on Graphs with Scarce Labels 8
Explaining Predictions in Graph Neural Networks 8
Hyperparameter Sensitivity in Complex Machine Learning Frameworks 8

Top Authors

AuthorPapers
Philip S. Yu169
Xiaofang Zhou85
Lei Chen77
Hui Xiong74
Xuemin Lin63
Ming-syan Chen60
Xuelong Li59
Wenjie Zhang48
Guoren Wang47
Jiawei Han46
Jianliang Xu43
Christian S. Jensen42
Li Qing41
Hongzhi Yin39
Chengqi Zhang38
Ying Zhang36
Yunjun Gao36
Xindong Wu35
Meng Wang34
Xinwang Liu34

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
Data Categorization Using Decision Trellises1999
Data Management Issues and Trade-Offs in CSCW Systems1999
Finding Interesting Patterns Using User Expectations1999
Guest Editor's Introduction to the Special Issue on Web Technologies1999
Induction By Attribute Elimination1999
Join Index Hierarchy: An Indexing Structure for Efficient Navigation in Object-Oriented Databases1999
JPernLite: Extensible Transaction Services for the WWW1999
Managing Complex Documents Over the WWW: A Case Study for XML1999
Mining Multiple-Level Association Rules in Large Databases1999
Multilevel Filtering for High-Dimensional Image Data: Why and How1999
Potential Cases, Methodologies, and Strategies of Synthesis of Solutions in Distributed Expert Systems1999
Proof of the Correctness of EMYCIN Sequential Propagation Under Conditional Independence Assumptions1999
Rule-induction and case-based reasoning: hybrid architectures appear advantageous1999
Spatial Databases - Accomplishments and Research Needs1999
State of the Art in Parallel Search Techniques for Discrete Optimization Problems1999
Symbolic Interpretation of Artificial Neural Networks1999
Temporal Data Management1999
Temporal Entity-Relationship Models - A Survey1999
The Indispensability of Dispensable Indexes1999
Addendum to "On Satisfiability, Equivalence, and Implication Problems Involving Conjunctive Queries in Database Systems"1998
ADOME: An Advanced Object Modeling Environment1998
A Multistep Approach for Shape Similarity Search in Image Databases1998
Data Resource Selection in Distributed Visual Information Systems.1998
Designing Access Methods for Bitemporal Databases1998
Effects of update techniques on main memory database system performance1998
Efficient Data Mining for Path Traversal Patterns1998
Efficient Differential Timeslice Computation1998
Fast and Effective Retrieval of Medical Tumor Shapes1998
Generating Broadcast Programs that Support Range Queries1998
Hierarchical Encoded Path Views for Path Query Processing: An Optimal Model and Its Performance Evaluation1998
Incremental Maintenance of Materialized Object-Oriented Views in MultiView: Strategies and Performance Evaluation1998
Performance Analysis of Three Text-Join Algorithms1998
Supporting Ranked Boolean Similarity Queries in MARS1998
Analysis of the n-Dimensional Quadtree Decomposition for Arbitrary Hyperectangles1997
A Transparent Schema-Evolution System Based on Object-Oriented View Technology1997
Default Logic as a Query Language1997
Divergence Control Algorithms for Epsilon Serializability1997
Efficient Scheduling of Page Access in Index-Based Join Processing1997
Feature Selection via Discretization1997
High-order pattern discovery from discrete-valued data1997
Implementation of tabled evaluation with delaying in Prolog1997
Modified fractal signature (MFS): a new approach to document analysis for automatic knowledge acquisition1997
Multiprocessor Document Allocation: A Genetic Algorithm Approach1997
Optimal Design of Multiple Hash Tables for Concurrency Control1997
Schema Evolution of an Object-Oriented Real-Time Database System for Manufacturing Automation1997
Semantics, Consistency, and Query Processing of Empirical Deductive Databases1997
Similarity Searching in Medical Image Databases1997
The Role of Polymorphic Reuse Mechanisms in Schema Evolution in an Object-Oriented Database1997
Using a Hash-Based Method with Transaction Trimming for Mining Association Rules1997
A Guide to the Literature on Learning Probabilistic Networks from Data1996

« prev Page 88/90 next »