Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleAugust 2024JUST ACCEPTED
Towards Prototype-Based Self-Explainable Graph Neural Network
ACM Transactions on Knowledge Discovery from Data (TKDD), Just Accepted https://doi.org/10.1145/3689647Graph Neural Networks (GNNs) have shown great ability in modeling graph-structured data for various domains. However, GNNs are known as black-box models that lack interpretability. Without understanding their inner working, we cannot fully trust them, ...
- research-articleAugust 2024JUST ACCEPTED
Graph Representation Learning enhanced Semi-supervised Feature Selection
ACM Transactions on Knowledge Discovery from Data (TKDD), Just Accepted https://doi.org/10.1145/3689428Feature selection is a key step in machine learning by eliminating features that are not related to the modeling target to create reliable and interpretable models. By exploring the potential complex correlations among features of unlabeled data, recently ...
- research-articleAugust 2024
Towards Faster Deep Graph Clustering via Efficient Graph Auto-Encoder
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 8Article No.: 202, Pages 1–23https://doi.org/10.1145/3674983Deep graph clustering (DGC) has been a promising method for clustering graph data in recent years. However, existing research primarily focuses on optimizing clustering outcomes by improving the quality of embedded representations, resulting in slow-speed ...
- research-articleApril 2024
ProtoMGAE: Prototype-Aware Masked Graph Auto-Encoder for Graph Representation Learning
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 6Article No.: 137, Pages 1–22https://doi.org/10.1145/3649143Graph self-supervised representation learning has gained considerable attention and demonstrated remarkable efficacy in extracting meaningful representations from graphs, particularly in the absence of labeled data. Two representative methods in this ...
- research-articleMarch 2024
Generation-based Multi-view Contrast for Self-supervised Graph Representation Learning
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 5Article No.: 130, Pages 1–17https://doi.org/10.1145/3645095Graph contrastive learning has made remarkable achievements in the self-supervised representation learning of graph-structured data. By employing perturbation function (i.e., perturbation on the nodes or edges of graph), most graph contrastive learning ...
-
- tutorialFebruary 2024
Graph Time-series Modeling in Deep Learning: A Survey
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 5Article No.: 119, Pages 1–35https://doi.org/10.1145/3638534Time-series and graphs have been extensively studied for their ubiquitous existence in numerous domains. Both topics have been separately explored in the field of deep learning. For time-series modeling, recurrent neural networks or convolutional neural ...
- research-articleFebruary 2024
ArieL: Adversarial Graph Contrastive Learning
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 4Article No.: 82, Pages 1–22https://doi.org/10.1145/3638054Contrastive learning is an effective unsupervised method in graph representation learning. The key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the ...
- research-articleFebruary 2024
Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 4Article No.: 85, Pages 1–22https://doi.org/10.1145/3635718Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking different trajectories to users with the exploration of complex mobility patterns. Existing works mainly rely on the recurrent neural framework to encode the temporal ...
- research-articleJanuary 2024
Graph Domain Adaptation: A Generative View
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 3Article No.: 60, Pages 1–24https://doi.org/10.1145/3631712Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited samples. However, ...
- research-articleOctober 2023
Structure-Driven Representation Learning for Deep Clustering
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 1Article No.: 31, Pages 1–25https://doi.org/10.1145/3623400As an important branch of unsupervised learning methods, clustering makes a wide contribution in the area of data mining. It is well known that capturing the group-discriminative properties of each sample for clustering is crucial. Among them, deep ...
- research-articleSeptember 2023
Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrast
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 1Article No.: 18, Pages 1–20https://doi.org/10.1145/3612931Self-supervised learning on graphs has recently drawn a lot of attention due to its independence from labels and its robustness in representation. Current studies on this topic mainly use static information such as graph structures but cannot well capture ...
- research-articleMay 2023
Combining Diverse Meta-Features to Accurately Identify Recurring Concept Drift in Data Streams
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 17, Issue 8Article No.: 107, Pages 1–36https://doi.org/10.1145/3587098Learning from streaming data is challenging as the distribution of incoming data may change over time, a phenomenon known as concept drift. The predictive patterns, or experience learned under one distribution may become irrelevant as conditions change ...
- research-articleMay 2023
A Generalized Deep Learning Clustering Algorithm Based on Non-Negative Matrix Factorization
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 17, Issue 7Article No.: 99, Pages 1–20https://doi.org/10.1145/3584862Clustering is a popular research topic in the field of data mining, in which the clustering method based on non-negative matrix factorization (NMF) has been widely employed. However, in the update process of NMF, there is no learning rate to guide the ...
- research-articleMarch 2023
Learnable Graph-Regularization for Matrix Decomposition
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 17, Issue 3Article No.: 32, Pages 1–20https://doi.org/10.1145/3544781Low-rank approximation models of data matrices have become important machine learning and data mining tools in many fields, including computer vision, text mining, bioinformatics, and many others. They allow for embedding high-dimensional data into low-...
- research-articleFebruary 2023
Dynamic Multi-View Graph Neural Networks for Citywide Traffic Inference
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 17, Issue 4Article No.: 53, Pages 1–22https://doi.org/10.1145/3564754Accurate citywide traffic inference is critical for improving intelligent transportation systems with smart city applications. However, this task is very challenging given the limited training data, due to the high cost of sensor installment and ...
- research-articleFebruary 2023
An Efficient Aggregation Method for the Symbolic Representation of Temporal Data
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 17, Issue 1Article No.: 5, Pages 1–22https://doi.org/10.1145/3532622Symbolic representations are a useful tool for the dimension reduction of temporal data, allowing for the efficient storage of and information retrieval from time series. They can also enhance the training of machine learning algorithms on time series ...
- research-articleMarch 2022
Evidence Transfer: Learning Improved Representations According to External Heterogeneous Task Outcomes
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 16, Issue 5Article No.: 85, Pages 1–22https://doi.org/10.1145/3502732Unsupervised representation learning tends to produce generic and reusable latent representations. However, these representations can often miss high-level features or semantic information, since they only observe the implicit properties of the dataset. ...
- research-articleNovember 2021
Toward Understanding and Evaluating Structural Node Embeddings
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 16, Issue 3Article No.: 58, Pages 1–32https://doi.org/10.1145/3481639While most network embedding techniques model the proximity between nodes in a network, recently there has been significant interest in structural embeddings that are based on node equivalences, a notion rooted in sociology: equivalences or positions are ...
- research-articleOctober 2021
DACHA: A Dual Graph Convolution Based Temporal Knowledge Graph Representation Learning Method Using Historical Relation
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 16, Issue 3Article No.: 46, Pages 1–18https://doi.org/10.1145/3477051Temporal knowledge graph (TKG) representation learning embeds relations and entities into a continuous low-dimensional vector space by incorporating temporal information. Latest studies mainly aim at learning entity representations by modeling entity ...
- research-articleApril 2021
TPmod: A Tendency-Guided Prediction Model for Temporal Knowledge Graph Completion
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 15, Issue 3Article No.: 41, Pages 1–17https://doi.org/10.1145/3443687Temporal knowledge graphs (TKGs) have become useful resources for numerous Artificial Intelligence applications, but they are far from completeness. Inferring missing events in temporal knowledge graphs is a fundamental and challenging task. However, most ...