CmaGraph: A TriBlocks Anomaly Detection Method in Dynamic Graph Using Evolutionary Community Representation Learning

Lin, Weiqin; Bao, Xianyu; Li, Mark Junjie

doi:10.1007/978-3-030-86362-3_9

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For similar motivations, Mu et al presented a novel approach to discovering and alleviating the potential spurious correlations by introducing two counterfactual generators and a recommender (Mu et al 2022). Apart from these, there have also been many counterfactual inference-based research on model interpretability (Lin, Lan, and Li 2021;Tan et al 2022;Abid, Yuksekgonul, and Zou 2022). However, we have not seen related research on counterfactual inference-based MIL methods tailored for instance prediction.…”

Section: Counterfactual Inferencementioning

confidence: 99%

Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference

Lin,

Zhuang,

et al. 2024

AAAI

View full text Add to dashboard Cite

Multiple instance learning is an effective paradigm for whole slide image (WSI) classification, where labels are only provided at the bag level. However, instance-level prediction is also crucial as it offers insights into fine-grained regions of interest. Existing multiple instance learning methods either solely focus on training a bag classifier or have the insufficient capability of exploring instance prediction. In this work, we propose a novel model-agnostic framework to boost existing multiple instance learning models, to improve the WSI classification performance in both bag and instance levels. Specifically, we propose a counterfactual inference-based sub-bag assessment method and a hierarchical instance searching strategy to help to search reliable instances and obtain their accurate pseudo labels. Furthermore, an instance classifier is well-trained to produce accurate predictions. The instance embedding it generates is treated as a prompt to refine the instance feature for bag prediction. This framework is model-agnostic, capable of adapting to existing multiple instance learning models, including those without specific mechanisms like attention. Extensive experiments on three datasets demonstrate the competitive performance of our method. Code will be available at https://github.com/centurion-crawler/CIMIL.

show abstract

Section: Counterfactual Inferencementioning

confidence: 99%

Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference

Lin,

Zhuang,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Alternatively, we can adapt advanced model-agnostic explanation methods (Yuan et al 2020) proposed for GNNs (on homogeneous graphs) to HGNs. These methods attribute model predictions to graph objects, such as nodes (Vu and Thai 2020), edges (Ying et al 2019;Luo et al 2020;Schlichtkrull, De Cao, and Titov 2020;Wang et al 2021b;Lin, Lan, and Li 2021) and subgraphs (Yuan et al 2021). Their goal is to learn or search for optimal graph objects that maximize mutual information with the predictions.…”

Section: Introductionmentioning

confidence: 99%

Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network

Deng

Shen

et al. 2023

AAAI

View full text Add to dashboard Cite

Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs. Despite the superior performance, insights about the predictions made from HGNs are obscure to humans. Existing explainability techniques are mainly proposed for GNNs on homogeneous graphs. They focus on highlighting salient graph objects to the predictions whereas the problem of how these objects affect the predictions remains unsolved. Given heterogeneous graphs with complex structures and rich semantics, it is imperative that salient objects can be accompanied with their influence paths to the predictions, unveiling the reasoning process of HGNs. In this paper, we develop xPath, a new framework that provides fine-grained explanations for black-box HGNs specifying a cause node with its influence path to the target node. In xPath, we differentiate the influence of a node on the prediction w.r.t. every individual influence path, and measure the influence by perturbing graph structure via a novel graph rewiring algorithm. Furthermore, we introduce a greedy search algorithm to find the most influential fine-grained explanations efficiently. Empirical results on various HGNs and heterogeneous graphs show that xPath yields faithful explanations efficiently, outperforming the adaptations of advanced GNN explanation approaches.

show abstract

Anomaly Detection in Dynamic Graphs Via Long Short-Term Temporal Attention Network

Gao,

Ma,

et al. 2023

2023 International Conference on Machine Learning and Cybernetics (ICMLC)

View full text Add to dashboard Cite

CmaGraph: A TriBlocks Anomaly Detection Method in Dynamic Graph Using Evolutionary Community Representation Learning

Cited by 4 publications

References 15 publications

Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference

Boosting Multiple Instance Learning Models for Whole Slide Image Classification: A Model-Agnostic Framework Based on Counterfactual Inference

Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network

Anomaly Detection in Dynamic Graphs Via Long Short-Term Temporal Attention Network

Contact Info

Product

Resources

About