Vassilis N. Ioannidis
Vassilis N. Ioannidis has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Georgios B. Giannakis
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
10 shared publications - Danai Koutra
University of Michigan
3 shared publications - Daniel Romero
Department of Information and Communication Technology, University of Agder, Grimstad, Norway
3 shared publications - Soji Adeshina
Amazon, Santa Clara, CA, USA
3 shared publications - Xiang Song
Amazon AWS AI, Santa Clara, CA, USA
3 shared publications - Antonio Garcia Marques
Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain
2 shared publications
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4457-4466
Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4457-4466
Open AccessHierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6318-6319
SKnow-LLM Workshop: Structured Knowledge for Large Language Models
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6318-6319
Open AccessSKnow-LLM Workshop: Structured Knowledge for Large Language Models
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3145-3154
Revisit Orthogonality in Graph-Regularized MLPs
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3145-3154
Open AccessRevisit Orthogonality in Graph-Regularized MLPs
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2662-2666
TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning
How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks? Graph Neural Networks (GNNs) have become the state-of-the-art approach for many high-impact, real-world graph applications. For feature-rich graphs, a prevalent practice involves directly utilizing a PM to generate features. Nevertheless, this practice is suboptimal as the node features extracted from PMs are graph-agnostic and prevent GNNs from fully utilizing the potential correlations between the graph structure and node features, leading to a decline in GNN performance. In this work, we seek to improve the node features obtained from a PM for graph tasks and introduce TouchUp-G, a "Detect & Correct" approach for refining node features extracted from PMs. TouchUp-G detects the alignment using a novel feature homophily metric and corrects the misalignment through a simple touchup on the PM. It is (a) General: applicable to any downstream graph task; (b) Multi-modal: able to improve raw features of any modality; (c) Principled: it is closely related to a novel metric, feature homophily, which we propose to quantify the alignment between the graph structure and node features; (d) Effective: achieving state-of-the-art results on four real-world datasets spanning different tasks and modalities.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2662-2666
Open AccessTouchUp-G: Improving Feature Representation through Graph-Centric Finetuning
How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks? Graph Neural Networks (GNNs) have become the state-of-the-art approach for many high-impact, real-world graph applications. For feature-rich graphs, a prevalent practice involves directly utilizing a PM to generate features. Nevertheless, this practice is suboptimal as the node features extracted from PMs are graph-agnostic and prevent GNNs from fully utilizing the potential correlations between the graph structure and node features, leading to a decline in GNN performance. In this work, we seek to improve the node features obtained from a PM for graph tasks and introduce TouchUp-G, a "Detect & Correct" approach for refining node features extracted from PMs. TouchUp-G detects the alignment using a novel feature homophily metric and corrects the misalignment through a simple touchup on the PM. It is (a) General: applicable to any downstream graph task; (b) Multi-modal: able to improve raw features of any modality; (c) Principled: it is closely related to a novel metric, feature homophily, which we propose to quantify the alignment between the graph structure and node features; (d) Effective: achieving state-of-the-art results on four real-world datasets spanning different tasks and modalities.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 994-1002
Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including the edges being predicted in the graph at training and/or test have outsized impact on the performance of low-degree nodes. We theoretically and empirically investigate how these practices impact node-level performance across different degrees. Specifically, we explore three issues that arise: (I1) overfitting; (I2) distribution shift; and (I3) implicit test leakage. The former two issues lead to poor generalizability to the test data, while the latter leads to overestimation of the model's performance and directly impacts the deployment of GNNs. To address these issues in a systematic way, we introduce an effective and efficient GNN training framework, SpotTarget, which leverages our insight on low-degree nodes: (1) at training time, it excludes a (training) edge to be predicted if it is incident to at least one low-degree node; and (2) at test time, it excludes all test edges to be predicted (thus, mimicking real scenarios of using GNNs, where the test data is not included in the graph). SpotTarget helps researchers and practitioners adhere to best practices for learning from graph data, which are frequently overlooked even by the most widely-used frameworks. Our experiments on various real-world datasets show that SpotTarget makes GNNs up to 15× more accurate in sparse graphs, and significantly improves their performance for low-degree nodes in dense graphs.
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 994-1002
Open AccessPitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including the edges being predicted in the graph at training and/or test have outsized impact on the performance of low-degree nodes. We theoretically and empirically investigate how these practices impact node-level performance across different degrees. Specifically, we explore three issues that arise: (I1) overfitting; (I2) distribution shift; and (I3) implicit test leakage. The former two issues lead to poor generalizability to the test data, while the latter leads to overestimation of the model's performance and directly impacts the deployment of GNNs. To address these issues in a systematic way, we introduce an effective and efficient GNN training framework, SpotTarget, which leverages our insight on low-degree nodes: (1) at training time, it excludes a (training) edge to be predicted if it is incident to at least one low-degree node; and (2) at test time, it excludes all test edges to be predicted (thus, mimicking real scenarios of using GNNs, where the test data is not included in the graph). SpotTarget helps researchers and practitioners adhere to best practices for learning from graph data, which are frequently overlooked even by the most widely-used frameworks. Our experiments on various real-world datasets show that SpotTarget makes GNNs up to 15× more accurate in sparse graphs, and significantly improves their performance for low-degree nodes in dense graphs.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the Acm Sigkdd Conference on Knowledge Discovery and Data Mining
- Vol. 2023, 5270-5281
Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applications with different graph schemas. To address this problem, we propose a framework of graph-aware language model pre-training (GaLM) on a large graph corpus, which incorporates large language models and graph neural networks, and a variety of fine-tuning methods on downstream applications. We conduct extensive experiments on Amazon's real internal datasets and large public datasets. Comprehensive empirical results and in-depth analysis demonstrate the effectiveness of our proposed methods along with lessons learned.
- 4 August 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the Acm Sigkdd Conference on Knowledge Discovery and Data Mining
- Vol. 2023, 5270-5281
Open AccessGraph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applications with different graph schemas. To address this problem, we propose a framework of graph-aware language model pre-training (GaLM) on a large graph corpus, which incorporates large language models and graph neural networks, and a variety of fine-tuning methods on downstream applications. We conduct extensive experiments on Amazon's real internal datasets and large public datasets. Comprehensive empirical results and in-depth analysis demonstrate the effectiveness of our proposed methods along with lessons learned.
- Open Access
- 18 March 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1-14
A knowledge graph of clinical trials ($\mathop {\mathtt {CTKG}}\limits$)Effective and successful clinical trials are essential in developing new drugs and advancing new treatments. However, clinical trials are very expensive and easy to fail. The high cost and low success rate of clinical trials motivate research on inferring knowledge from existing clinical trials in innovative ways for designing future clinical trials. In this manuscript, we present our efforts on constructing the first publicly available Clinical Trials Knowledge Graph, denoted as $$\mathop {\mathtt {CTKG}}\limits$$ . $$\mathop {\mathtt {CTKG}}\limits$$ includes nodes representing medical entities in clinical trials (e.g., studies, drugs and conditions), and edges representing the relations among these entities (e.g., drugs used in studies). Our embedding analysis demonstrates the potential utilities of $$\mathop {\mathtt {CTKG}}\limits$$ in various applications such as drug repurposing and similarity search, among others.- 18 March 2022
- Published by Springer Nature in Scientific Reports
- Vol. 12 (1) , 1-14
Open AccessA knowledge graph of clinical trials ($\mathop {\mathtt {CTKG}}\limits$)Effective and successful clinical trials are essential in developing new drugs and advancing new treatments. However, clinical trials are very expensive and easy to fail. The high cost and low success rate of clinical trials motivate research on inferring knowledge from existing clinical trials in innovative ways for designing future clinical trials. In this manuscript, we present our efforts on constructing the first publicly available Clinical Trials Knowledge Graph, denoted as $$\mathop {\mathtt {CTKG}}\limits$$ . $$\mathop {\mathtt {CTKG}}\limits$$ includes nodes representing medical entities in clinical trials (e.g., studies, drugs and conditions), and edges representing the relations among these entities (e.g., drugs used in studies). Our embedding analysis demonstrates the potential utilities of $$\mathop {\mathtt {CTKG}}\limits$$ in various applications such as drug repurposing and similarity search, among others. - 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5499-5503
Unveiling Anomalous Nodes Via Random Sampling and Consensus on Graphs
The present paper develops a graph-based sampling and consensus (GraphSAC) approach to effectively detect anomalous nodes in large-scale graphs. GraphSAC randomly draws sub-sets of nodes, and relies on graph-aware criteria to judiciously filter out sets contaminated by anomalous nodes, before employing a semi-supervised learning (SSL) module to estimate nominal label distributions per node. These learned nominal distributions are minimally affected by the anomalous nodes, and hence can be directly adopted for anomaly detection. The per-draw complexity grows linearly with the number of edges, which implies efficient SSL, while draws can be run in parallel, thereby ensuring scalability to large graphs. GraphSAC is tested under different anomaly generation models based on random walks, as well as contemporary adversarial attacks for graph data. Experiments with real-world graphs show-case the advantage of GraphSAC relative to state-of-the-art alternatives.
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5499-5503
Unveiling Anomalous Nodes Via Random Sampling and Consensus on Graphs
The present paper develops a graph-based sampling and consensus (GraphSAC) approach to effectively detect anomalous nodes in large-scale graphs. GraphSAC randomly draws sub-sets of nodes, and relies on graph-aware criteria to judiciously filter out sets contaminated by anomalous nodes, before employing a semi-supervised learning (SSL) module to estimate nominal label distributions per node. These learned nominal distributions are minimally affected by the anomalous nodes, and hence can be directly adopted for anomaly detection. The per-draw complexity grows linearly with the number of edges, which implies efficient SSL, while draws can be run in parallel, thereby ensuring scalability to large graphs. GraphSAC is tested under different anomaly generation models based on random walks, as well as contemporary adversarial attacks for graph data. Experiments with real-world graphs show-case the advantage of GraphSAC relative to state-of-the-art alternatives.
- 7 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 6535-6546
Tensor Graph Convolutional Networks for Multi-Relational and Robust Learning
The era of “data deluge” has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. Key aspects of the novel TGCN architecture are the dynamic adaptation to different relations in the tensor graph via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parameterization. The ultimate goal is to design a powerful learning architecture able to: discover complex and highly nonlinear data associations, combine (and select) multiple types of relations, scale gracefully with the graph size, and remain robust to perturbations on the graph edges. The proposed architecture is relevant not only in applications where the nodes are naturally involved in different relations (e.g., a multi-relational graph capturing family, friendship and work relations in a social network), but also in robust learning setups where the graph entails a certain level of uncertainty, and the different tensor slabs correspond to different versions (realizations) of the nominal graph. Numerical tests showcase that the proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
- 7 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 6535-6546
Tensor Graph Convolutional Networks for Multi-Relational and Robust Learning
The era of “data deluge” has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. Key aspects of the novel TGCN architecture are the dynamic adaptation to different relations in the tensor graph via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parameterization. The ultimate goal is to design a powerful learning architecture able to: discover complex and highly nonlinear data associations, combine (and select) multiple types of relations, scale gracefully with the graph size, and remain robust to perturbations on the graph edges. The proposed architecture is relevant not only in applications where the nodes are naturally involved in different relations (e.g., a multi-relational graph capturing family, friendship and work relations in a social network), but also in robust learning setups where the graph entails a certain level of uncertainty, and the different tensor slabs correspond to different versions (realizations) of the nominal graph. Numerical tests showcase that the proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
- 18 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (3) , 1232-1246
Efficient and Stable Graph Scattering Transforms via Pruning
Graph convolutional networks (GCNs) have well-documented performance in various graph learning tasks, but their analysis is still at its infancy. Graph scattering transforms (GSTs) offer training-free deep GCN models, and are amenable to generalization and stability analyses. The price paid by GSTs is exponential complexity that increases with the number of layers. This discourages deployment of GSTs when a deep architecture is needed. The present work addresses the complexity limitation of GSTs by introducing an efficient so-termed pruned (p)GST approach. The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs. Stability of the novel pGSTs is established when the input graph data or the network structure are perturbed. Furthermore, the sensitivity of pGST to random and localized signal perturbations is investigated analytically and experimentally. Numerical tests showcase that pGST performs comparably to the baseline GST at considerable computational savings. Furthermore, pGST achieves comparable performance to state-of-the-art GCNs in graph and 3D point cloud classification tasks. Upon analyzing the pGST pruning patterns, graph data in different domains call for different network architectures, and the pruning algorithm may guide the design choices for contemporary GCNs.
- 18 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (3) , 1232-1246
Efficient and Stable Graph Scattering Transforms via Pruning
Graph convolutional networks (GCNs) have well-documented performance in various graph learning tasks, but their analysis is still at its infancy. Graph scattering transforms (GSTs) offer training-free deep GCN models, and are amenable to generalization and stability analyses. The price paid by GSTs is exponential complexity that increases with the number of layers. This discourages deployment of GSTs when a deep architecture is needed. The present work addresses the complexity limitation of GSTs by introducing an efficient so-termed pruned (p)GST approach. The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs. Stability of the novel pGSTs is established when the input graph data or the network structure are perturbed. Furthermore, the sensitivity of pGST to random and localized signal perturbations is investigated analytically and experimentally. Numerical tests showcase that pGST performs comparably to the baseline GST at considerable computational savings. Furthermore, pGST achieves comparable performance to state-of-the-art GCNs in graph and 3D point cloud classification tasks. Upon analyzing the pGST pruning patterns, graph data in different domains call for different network architectures, and the pruning algorithm may guide the design choices for contemporary GCNs.