Adversarial Robustness of Probabilistic Network Embedding for Link Prediction

• URL: http://arxiv.org/abs/2107.01936v1
• Date: Mon, 5 Jul 2021 11:07:35 GMT
• Title: Adversarial Robustness of Probabilistic Network Embedding for Link Prediction
• Authors: Xi Chen, Bo Kang, Jefrey Lijffijt, Tijl De Bie
• Abstract summary: We study adversarial robustness of Conditional Network Embedding (CNE) for link prediction. We measure the sensitivity of the link predictions of the model to small adversarial perturbations of the network. Our approach allows one to identify the links and non-links in the network that are most vulnerable to such perturbations.
• Score: 24.335469995826244
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In today's networked society, many real-world problems can be formalized as predicting links in networks, such as Facebook friendship suggestions, e-commerce recommendations, and the prediction of scientific collaborations in citation networks. Increasingly often, link prediction problem is tackled by means of network embedding methods, owing to their state-of-the-art performance. However, these methods lack transparency when compared to simpler baselines, and as a result their robustness against adversarial attacks is a possible point of concern: could one or a few small adversarial modifications to the network have a large impact on the link prediction performance when using a network embedding model? Prior research has already investigated adversarial robustness for network embedding models, focused on classification at the node and graph level. Robustness with respect to the link prediction downstream task, on the other hand, has been explored much less. This paper contributes to filling this gap, by studying adversarial robustness of Conditional Network Embedding (CNE), a state-of-the-art probabilistic network embedding model, for link prediction. More specifically, given CNE and a network, we measure the sensitivity of the link predictions of the model to small adversarial perturbations of the network, namely changes of the link status of a node pair. Thus, our approach allows one to identify the links and non-links in the network that are most vulnerable to such perturbations, for further investigation by an analyst. We analyze the characteristics of the most and least sensitive perturbations, and empirically confirm that our approach not only succeeds in identifying the most vulnerable links and non-links, but also that it does so in a time-efficient manner thanks to an effective approximation.

Related papers

• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• An Approach for Link Prediction in Directed Complex Networks based on Asymmetric Similarity-Popularity [0.0]
  This paper introduces a link prediction method designed explicitly for directed networks. It is based on the similarity-popularity paradigm, which has recently proven successful in undirected networks. The algorithms approximate the hidden similarities as shortest path distances using edge weights that capture and factor out the links' asymmetry and nodes' popularity.
  arXiv  Detail & Related papers  (2022-07-15T11:03:25Z)
• A Learning Convolutional Neural Network Approach for Network Robustness Prediction [13.742495880357493]
  Network robustness is critical for various societal and industrial networks again malicious attacks. In this paper, an improved method for network robustness prediction is developed based on learning feature representation using convolutional neural network (LFR-CNN) In this scheme, higher-dimensional network data are compressed to lower-dimensional representations, and then passed to a CNN to perform robustness prediction.
  arXiv  Detail & Related papers  (2022-03-20T13:45:55Z)
• Link Prediction with Contextualized Self-Supervision [63.25455976593081]
  Link prediction aims to infer the existence of a link between two nodes in a network. Traditional link prediction algorithms are hindered by three major challenges -- link sparsity, node attribute noise and network dynamics. We propose a Contextualized Self-Supervised Learning framework that fully exploits structural context prediction for link prediction.
  arXiv  Detail & Related papers  (2022-01-25T03:12:32Z)
• BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
  Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning. We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction. BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
  arXiv  Detail & Related papers  (2021-12-13T17:35:54Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction [69.1473775184952]
  We introduce a realistic problem of few-shot out-of-graph link prediction. We tackle this problem with a novel transductive meta-learning framework. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
  arXiv  Detail & Related papers  (2020-06-11T17:42:46Z)
• Link Prediction for Temporally Consistent Networks [6.981204218036187]
  Link prediction estimates the next relationship in dynamic networks. The use of adjacency matrix to represent dynamically evolving networks limits the ability to analytically learn from heterogeneous, sparse, or forming networks. We propose a new method of canonically representing heterogeneous time-evolving activities as a temporally parameterized network model.
  arXiv  Detail & Related papers  (2020-06-06T07:28:03Z)
• Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness [97.67477497115163]
  We use mode connectivity to study the adversarial robustness of deep neural networks. Our experiments cover various types of adversarial attacks applied to different network architectures and datasets. Our results suggest that mode connectivity offers a holistic tool and practical means for evaluating and improving adversarial robustness.
  arXiv  Detail & Related papers  (2020-04-30T19:12:50Z)
• Heuristics for Link Prediction in Multiplex Networks [15.637077180633735]
  We propose a novel framework and three families of families for multiplex network link prediction. We show that the proposeds show increased performance with the richness of connection type correlation structure and significantly outperform their baselines for ordinary networks with a single connection type.
  arXiv  Detail & Related papers  (2020-04-09T17:36:18Z)
• NEW: A Generic Learning Model for Tie Strength Prediction in Networks [5.834475036139535]
  Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks. We propose a new computational framework called Neighborhood Estimating Weight (NEW) NEW is purely driven by the basic structure information of the network and has the flexibility for adapting to diverse types of networks.
  arXiv  Detail & Related papers  (2020-01-15T13:02:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.