Prototypical Graph Contrastive Learning

Lin, Shuai; Liu, Chen; Zhou, Pan; Hu, Zi-Yuan; Wang, Shuojia; Zhao, Ruihui; Zheng, Yefeng; Lin, Liang; Xing, Eric P.; Liang, Xiaodan

doi:10.1109/tnnls.2022.3191086

Cited by 58 publications

(20 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These messages are then propagated with various message-passing mechanisms to refine node representations, which are then utilized for downstream tasks [8], [10], [21]. Explorations are made by disentangling the propagation process [28], [29], [30] or utilizing external prototypes [31], [32]. Research has also been conducted on the expressive power [33], [34] and potential biases introduced by different kernels [35], [36] for the design of more effective GNNs.…”

Section: Graph Neural Networkmentioning

confidence: 99%

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Zhao¹,

Luo²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making predictions. Though various algorithms are proposed, most of them formalize this task by searching the minimal subgraph which can preserve original predictions. However, an inductive bias is deep-rooted in this framework: several subgraphs can result in the same or similar outputs as the original graphs. Consequently, they have the danger of providing spurious explanations and failing to provide consistent explanations. Applying them to explain weakly-performed GNNs would further amplify these issues. To address this problem, we theoretically examine the predictions of GNNs from the causality perspective. Two typical reasons for spurious explanations are identified: confounding effect of latent variables like distribution shift, and causal factors distinct from the original input. Observing that both confounding effects and diverse causal rationales are encoded in internal representations, we propose a new explanation framework with an auxiliary alignment loss, which is theoretically proven to be optimizing a more faithful explanation objective intrinsically. Concretely for this alignment loss, a set of different perspectives are explored: anchor-based alignment, distributional alignment based on Gaussian mixture models, mutual-information-based alignment, etc. A comprehensive study is conducted both on the effectiveness of this new framework in terms of explanation faithfulness/consistency and on the advantages of these variants. For our codes, please refer to the following URL link: https://github.com/TianxiangZhao/GraphNNExplanation.

show abstract

Section: Graph Neural Networkmentioning

confidence: 99%

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Zhao¹,

Luo²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Liang .et.al [35] has been proposed to use graph to encode the dependencies of regions as vertices, edges of a graph with different pixels to measure the similarity between features. beyond regular grids, learn to graph representation for image or feature map, instead of just passing information on the graph.…”

Section: B Contextual Informationmentioning

confidence: 99%

CFNet: An Eigenvalue Preserved Approach to Multiscale Building Segmentation in High-Resolution Remote Sensing Images

Liu

Bilal

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In recent years, AI and Deep Learning (DL) methods have been widely used for object classification, recognition, and segmentation of high-resolution multispectral remote sensing images. These DL-based solutions perform better compare to traditional spectral algorithms but still suffer from insufficient optimization of global and local features of object context. In addition, failure of code-data isolation and/or disclosure of detailed eigenvalues causes serious privacy and even secret leakage due to the sensitivity of high-resolution remote sensing data and their processing mechanisms. In this paper, Class Feature (CF) modules have been presented in the decoder part of an attention-based CNN network to distinguish between building and non-building (background) area. In this way, context features of a focused object can be extracted with more details being processed, whilst the resolution of images is maintained. The reconstructed local and global feature values and dependencies in the proposed model are maintained by reconfiguring multiple effective attention modules with contextual dependencies to achieve better results for the eigenvalue. According to quantitative results and their visualization, the proposed model has depicted better performance over others' work using two largescale building remote sensing datasets. The F1-score of this model reached 87.91 and 89.58 on WHU Buildings Dataset and Massachusetts Buildings Dataset, respectively, which exceeded the other semantic segmentation models.

show abstract

“…On the other hand, some works design various auxiliary tasks under specific settings [31,36,73,75]. Specifically, MTRec [31] takes link prediction for network dynamic modeling as an auxiliary of the recommendation task.…”

Section: Auxiliary With Mainmentioning

confidence: 99%

“…Specifically, MTRec [31] takes link prediction for network dynamic modeling as an auxiliary of the recommendation task. PICO [36] considers task relevance between CTR and CVR as auxiliary. MTAE [75] predicts the winning probability as auxiliary.…”

Section: Auxiliary With Mainmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Task Deep Recommender Systems: A Survey

Wang¹,

Lam²,

Wong³

et al. 2023

Preprint

View full text Add to dashboard Cite

Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.

show abstract

Prototypical Graph Contrastive Learning

Cited by 58 publications

References 48 publications

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

CFNet: An Eigenvalue Preserved Approach to Multiscale Building Segmentation in High-Resolution Remote Sensing Images

Multi-Task Deep Recommender Systems: A Survey

Contact Info

Product

Resources

About