Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperAugust 2024
Knowledge Graph Enhancement for Improved Natural Language Health Question Answering using Large Language Models
SSDBM '24: Proceedings of the 36th International Conference on Scientific and Statistical Database ManagementArticle No.: 14, Pages 1–4https://doi.org/10.1145/3676288.3676289In this paper we present a method for enhancing Question Answering (QA) systems by iteratively improving Knowledge Graphs (KGs) with a focus on maintaining monotonicity in the enhancement process. We introduce a mathematical framework employing ...
- research-articleFebruary 2024
Graph-based Text Classification by Contrastive Learning with Text-level Graph Augmentation
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 4Article No.: 77, Pages 1–21https://doi.org/10.1145/3638353Text Classification (TC) is a fundamental task in the information retrieval community. Nowadays, the mainstay TC methods are built on the deep neural networks, which can learn much more discriminative text features than the traditional shallow learning ...
- short-paperOctober 2023
Investigating Natural and Artificial Dynamics in Graph Data Mining and Machine Learning
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementPages 5173–5176https://doi.org/10.1145/3583780.3616007The complexity of relationships between entities is increasing in the era of big data, leading to a growing interest in graph (network) data, owing to its ability to encode intricate relational information. Graph data mining and machine learning methods ...
- research-articleOctober 2023
Improving Long-Tail Item Recommendation with Graph Augmentation
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementPages 1707–1716https://doi.org/10.1145/3583780.3614929The ubiquitous long-tail distribution of inherent user behaviors results in worse recommendation performance for the items with fewer user records (i.e., tail items) than those with richer ones (i.e., head items). Graph-based recommendation methods (e.g.,...
- research-articleJuly 2023
Contrastive Learning for Signed Bipartite Graphs
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalPages 1629–1638https://doi.org/10.1145/3539618.3591655This paper is the first to use contrastive learning to improve the robustness of graph representation learning for signed bipartite graphs, which are commonly found in social networks, recommender systems, and paper review platforms. Existing contrastive ...
-
- research-articleApril 2023
Knowledge Graph Completion with Counterfactual Augmentation
WWW '23: Proceedings of the ACM Web Conference 2023Pages 2611–2620https://doi.org/10.1145/3543507.3583401Graph Neural Networks (GNNs) have demonstrated great success in Knowledge Graph Completion (KGC) by modeling how entities and relations interact in recent years. However, most of them are designed to learn from the observed graph structure, which ...
- tutorialFebruary 2023
Natural and Artificial Dynamics in GNNs: A Tutorial
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningPages 1252–1255https://doi.org/10.1145/3539597.3572726In the big data era, the relationship between entities becomes more complex. Therefore, graph (or network) data attracts increasing research attention for carrying complex relational information. For a myriad of graph mining/learning tasks, graph neural ...
- short-paperOctober 2022
DISCO: Comprehensive and Explainable Disinformation Detection
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementPages 4848–4852https://doi.org/10.1145/3511808.3557202Disinformation refers to false information deliberately spread to influence the general public, and the negative impact of disinformation on society can be observed in numerous issues, such as political agendas and manipulating financial markets. In ...
- research-articleOctober 2022
DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification
MM '22: Proceedings of the 30th ACM International Conference on MultimediaPages 3470–3479https://doi.org/10.1145/3503161.3548012Graph neural networks (GNNs) have achieved state-of-the-art results on graph classification tasks. They have been primarily studied in cases of supervised end-to-end training, which requires abundant task-specific labels. Unfortunately, annotating ...
- research-articleAugust 2022
Enhancing Machine Learning Approaches for Graph Optimization Problems with Diversifying Graph Augmentation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2191–2201https://doi.org/10.1145/3534678.3539437Recently, many machine learning-based approaches that effectively solve graph optimization problems have been proposed. These approaches are usually trained on graphs randomly generated with graph generators or sampled from existing datasets. However, we ...
- research-articleAugust 2022
Robust Tensor Graph Convolutional Networks via T-SVD based Graph Augmentation
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 2090–2099https://doi.org/10.1145/3534678.3539436Graph Neural Networks (GNNs) have exhibited their powerful ability of tackling nontrivial problems on graphs. However, as an extension of deep learning models to graphs, GNNs are vulnerable to noise or adversarial attacks due to the underlying ...
- research-articleOctober 2021
Video Representation Learning with Graph Contrastive Augmentation
MM '21: Proceedings of the 29th ACM International Conference on MultimediaPages 3043–3051https://doi.org/10.1145/3474085.3475510Contrastive-based self-supervised learning for image representations has significantly closed the gap with supervised learning. A natural extension of image-based contrastive learning methods to the video domain is to fully exploit the temporal ...
- research-articleAugust 2018
Improving the Betweenness Centrality of a Node by Adding Links
- Elisabetta Bergamini,
- Pierluigi Crescenzi,
- Gianlorenzo D'angelo,
- Henning Meyerhenke,
- Lorenzo Severini,
- Yllka Velaj
ACM Journal of Experimental Algorithmics (JEA), Volume 23Article No.: 1.5, Pages 1–32https://doi.org/10.1145/3166071Betweenness is a well-known centrality measure that ranks the nodes according to their participation in the shortest paths of a network. In several scenarios, having a high betweenness can have a positive impact on the node itself. Hence, in this ...
- research-articleJuly 2016
Greedily Improving Our Own Closeness Centrality in a Network
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 11, Issue 1Article No.: 9, Pages 1–32https://doi.org/10.1145/2953882The closeness centrality is a well-known measure of importance of a vertex within a given complex network. Having high closeness centrality can have positive impact on the vertex itself: hence, in this paper we consider the optimization problem of ...
- research-articleApril 2016
On the Maximum Betweenness Improvement Problem
Electronic Notes in Theoretical Computer Science (ENTCS) (ENTCS), Volume 322, Issue CPages 153–168https://doi.org/10.1016/j.entcs.2016.03.011The betweenness is a well-known measure of centrality of a node in a network. We consider the problem of determining how much a node can increase its betweenness centrality by creating a limited amount of new edges incident to it. If the graph is ...
- research-articleApril 2016
Generic route repair: augmenting wireless ad hoc sensor networks for local connectivity
IPSN '16: Proceedings of the 15th International Conference on Information Processing in Sensor NetworksArticle No.: 12, Pages 1–10Routes in a wireless network can be repaired reactively after node failures by broadcasting the message across the neighborhood of the failed node. This broadcast problem is easily solvable, if the neighborhood of every node in the network induces a ...
- posterOctober 2011
Suggesting ghost edges for a smaller world
CIKM '11: Proceedings of the 20th ACM international conference on Information and knowledge managementPages 2305–2308https://doi.org/10.1145/2063576.2063952Small changes in the network topology can have dramatic effects on its capacity to disseminate information. In this paper, we consider the problem of adding a small number of ghost edges in the network in order to minimize the average shortest-path ...
- articleOctober 2004
On the hardness of constructing minimal 2-connected spanning subgraphs in complete graphs with sharpened triangle inequality
- Hans-Joachim Böckenhauer,
- Dirk Bongartz,
- Juraj Hromkovič,
- Ralf Klasing,
- Guido Proietti,
- Sebastian Seibert,
- Walter Unger
Theoretical Computer Science (TCSC), Volume 326, Issue 1-3Pages 137–153https://doi.org/10.1016/j.tcs.2004.06.019In this paper we investigate the problem of finding a 2-connected spanning subgraph of minimal cost in a complete and weighted graph G. This problem is known to be APX-hard, for both the edge and the vertex connectivity case. Here we prove that the APX-...
- articleJanuary 2004
Constrained Edge-Splitting Problems
SIAM Journal on Discrete Mathematics (SIDMA), Volume 17, Issue 1Pages 88–102https://doi.org/10.1137/S0895480199364483Splitting off two edges su,sv in a graph G means deleting su,sv and adding a new edge uv. Let G=(V+s,E) be k-edge-connected in V ($k\geq 2$) and let d(s) be even. Lovász proved that the edges incident to s can be split off in pairs in a such a way that ...
- articleMarch 2003
An approximation for finding a smallest 2-edge-connected subgraph containing a specified spanning tree
Discrete Applied Mathematics (DAMA), Volume 126, Issue 1Pages 83–113https://doi.org/10.1016/S0166-218X(02)00218-4Given a graph G=(V,E) and a tree T =(V,F) with E ∩ F = φ such that G + T =(V,F ∪ E) is 2-edge-connected, we consider the problem of finding a smallest 2-edge-connected spanning subgraph (V,F ∪ E') of G + T containing T. The problem, which is known to be ...