Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method

Feng, Fuli; Huang, Weiran; He, Xiangnan; Xin, Xin; Wang, Qifan; Chua, Tat-Seng

doi:10.1145/3404835.3462971

Cited by 50 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Single network embedding methods [8,11,13,18,60,74] learn an information preserving embedding of a single-view network for node classification, node clustering and many other related tasks. A spectral based method [3] has been proposed, which uses the top-k eigenvectors to represent the network nodes.…”

Section: Related Work 21 Single Network Embeddingmentioning

confidence: 99%

Deep Partial Multiplex Network Embedding

Wang¹,

Fang²,

Ravula³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks. Realworld networks are usually with multiplex or having multi-view representations from different relations. Recently, there has been increasing interest in network embedding on multiplex data. However, most existing multiplex approaches assume that the data is complete in all views. But in real applications, it is often the case that each view suffers from the missing of some data and therefore results in partial multiplex data.In this paper, we present a novel Deep Partial Multiplex Network Embedding approach to deal with incomplete data. In particular, the network embeddings are learned by simultaneously minimizing the deep reconstruction loss with the autoencoder neural network, enforcing the data consistency across views via common latent subspace learning, and preserving the data topological structure within the same network through graph Laplacian. We further prove the orthogonal invariant property of the learned embeddings and connect our approach with the binary embedding techniques. Experiments on four multiplex benchmarks demonstrate the superior performance of the proposed approach over several stateof-the-art methods on node classification, link prediction and clustering tasks. CCS CONCEPTS• Information systems → Web searching and information discovery.

show abstract

Section: Related Work 21 Single Network Embeddingmentioning

confidence: 99%

Deep Partial Multiplex Network Embedding

Wang¹,

Fang²,

Ravula³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Causal Recommendation. Causal inference has been widely used in many machine learning applications, spanning from computer vision [23,34], natural language processing [11,12,43], to information retrieval [4]. In recommendation, most works on causal inference [25] focus on debiasing various biases in user feedback, including position bias [18], clickbait issue [37], and popularity bias [45].…”

Section: Related Workmentioning

confidence: 99%

Deconfounded Recommendation for Alleviating Bias Amplification

Wang

Feng

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

Self Cite

127

View full text Add to dashboard Cite

Recommender systems usually amplify the biases in the data. The model learned from historical interactions with imbalanced item distribution will amplify the imbalance by over-recommending items from the majority groups. Addressing this issue is essential for a healthy ecosystem of recommendation in the long run. Existing work applies bias control to the ranking targets (e.g., calibration, fairness, and diversity), but ignores the true reason for bias amplification and trades off the recommendation accuracy.In this work, we scrutinize the cause-effect factors for bias amplification, identifying the main reason lies in the confounding effect of imbalanced item distribution on user representation and prediction score. The existence of such confounder pushes us to go beyond merely modeling the conditional probability and embrace the causal modeling for recommendation. Towards this end, we propose a Deconfounded Recommender System (DecRS), which models the causal effect of user representation on the prediction score. The key to eliminating the impact of the confounder lies in backdoor adjustment, which is however difficult to do due to the infinite sample space of the confounder. For this challenge, we contribute an approximation operator for backdoor adjustment which can be easily plugged into most recommender models. Lastly, we devise an inference strategy to dynamically regulate backdoor adjustment according to user status. We instantiate DecRS on two representative models FM [32] and NFM [16], and conduct extensive experiments over two benchmarks to validate the superiority of our proposed DecRS.

show abstract

“…5.0.2 Causal Inference. Recently, causal inference [24,25] has attracted increasing attention in information retrieval and multimedia for removing dataset biases in domain-specific applications, such as recommendation [8,27,37,38,43], visual dialog [26], segmentation [49], unsupervised feature learning [36], video action localization [19], and scene graph [49], etc. The general purpose of causal inference is to empower the models the ability of pursuing the causal effect, thus leading to more robust decision.…”

Section: Related Workmentioning

confidence: 99%

Deconfounded Video Moment Retrieval with Causal Intervention

Yang

Feng

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

150

View full text Add to dashboard Cite

We tackle the task of video moment retrieval (VMR), which aims to localize a specific moment in a video according to a textual query. Existing methods primarily model the matching relationship between query and moment by complex cross-modal interactions. Despite their effectiveness, current models mostly exploit dataset biases while ignoring the video content, thus leading to poor generalizability. We argue that the issue is caused by the hidden confounder in VMR, i.e., temporal location of moments, that spuriously correlates the model input and prediction. How to design robust matching models against the temporal location biases is crucial but, as far as we know, has not been studied yet for VMR.To fill the research gap, we propose a causality-inspired VMR framework that builds structural causal model to capture the true effect of query and video content on the prediction. Specifically, we develop a Deconfounded Cross-modal Matching (DCM) method to remove the confounding effects of moment location. It first disentangles moment representation to infer the core feature of visual content, and then applies causal intervention on the disentangled multimodal input based on backdoor adjustment, which forces the model to fairly incorporate each possible location of the target into consideration. Extensive experiments clearly show that our approach can achieve significant improvement over the state-of-theart methods in terms of both accuracy and generalization (Codes: https://github.com/Xun-Yang/Causal_Video_Moment_Retrieval). CCS CONCEPTS• Information systems → Multimedia and multimodal retrieval.

show abstract

Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method

Cited by 50 publications

References 38 publications

Deep Partial Multiplex Network Embedding

Deep Partial Multiplex Network Embedding

Deconfounded Recommendation for Alleviating Bias Amplification

Deconfounded Video Moment Retrieval with Causal Intervention

Contact Info

Product

Resources

About