SSAR-GNN: Self-Supervised Artist Recommendation with Graph Neural Networks

Wang, Menghan; Rao, Xuan; Chen, Lisi; Shang, Shuo; Zhang, Binbin

doi:10.21203/rs.3.rs-1835327/v1

Cited by 6 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We follow the public data splits as [14,42]. We compare GraphMAE2 with state-of-the-art self-supervised graph learning methods, including contrastive methods, DGI [42], MVGRL [14], GRACE [57], BGRL [39], InfoGCL [48], CCA-SSG [54], and GGD [55] as well as generative methods GAE [24], Graph-MAE [18]. For the evaluation, we employ the linear probing mentioned above and report the average performance of accuracy on the test nodes based on 20 random initialization.…”

Section: Evaluating On Small-scale Datasetsmentioning

confidence: 99%

“…BGRL [39] uses an online encoder and a target encoder to contrast two augmented versions without negative samples. CCA-SSG [54] leverages a feature-level objective for graph SSL, inspired by Canonical Correlation Analysis methods.…”

Section: Graph Self-supervised Learningmentioning

confidence: 99%

“…For large datasets, we choose four baselines GRACE [57], BGRL [39], CCA-SSG [54] and GraphMAE [18]. To have a fair comparison, we download the public source code and use the GAT backbone.…”

Section: A Appendix A1 Theorem For Local Clusteringmentioning

confidence: 99%

“…Baselines. We compare GraphMAE2 with state-of-the-art selfsupervised graph learning methods, including contrastive methods, GRACE [57], BGRL [39], CCA-SSG [54], and GGD [55] as well as a generative method GraphMAE [18]. Other methods are not compared because they are not scalable to large graphs, e.g., MVGRL [14], or the source code has not been released, e.g., In-foGCL [48].…”

Section: Evaluating On Large-scale Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

Hou

Cen

et al. 2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data. Among both sets of graph SSL techniques, the masked graph autoencoders (e.g., GraphMAE)-one type of generative methods-have recently produced promising results. The idea behind this is to reconstruct the node features (or structures)-that are randomly masked from the input-with the autoencoder architecture. However, the performance of masked feature reconstruction naturally relies on the discriminability of the input features and is usually vulnerable to disturbance in the features. In this paper, we present a masked self-supervised learning framework 1 GraphMAE2 with the goal of overcoming this issue. The idea is to impose regularization on feature reconstruction for graph SSL. Specifically, we design the strategies of multi-view random re-mask decoding and latent representation prediction to regularize the feature reconstruction. The multi-view random re-mask decoding is to introduce randomness into reconstruction in the feature space, while the latent representation prediction is to enforce the reconstruction in the embedding space. Extensive experiments show that GraphMAE2 can consistently generate top results on various public datasets, including at least 2.45% improvements over state-of-the-art baselines on ogbn-Papers100M with 111M nodes and 1.6B edges.

show abstract

Section: Evaluating On Small-scale Datasetsmentioning

confidence: 99%

Section: Graph Self-supervised Learningmentioning

confidence: 99%

“…For large datasets, we choose four baselines GRACE [57], BGRL [39], CCA-SSG [54] and GraphMAE [18]. To have a fair comparison, we download the public source code and use the GAT backbone.…”

Section: A Appendix A1 Theorem For Local Clusteringmentioning

confidence: 99%

Section: Evaluating On Large-scale Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

Hou

Cen

et al. 2023

Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

show abstract

“…We consider both contrastive methods and generative methods as baselines. Node-level GCL baselines are compared in the node classification task, including DGI (Velickovic et al 2019), MVGRL (Hassani and Ahmadi 2020), GRACE, BGRL (Thakoor et al 2022), InfoGCL (Xu et al 2021), and CCA-SSG (Zhang et al 2021). In graph classification task, compared graph-level GCL baselines are Graph2vec (Narayanan et al 2017), InfoGraph (Sun et al 2020), GraphCL, JOAO (You et al 2021), GCC, MVGRL, and InfoGCL.…”

Section: Evaluation Setupsmentioning

confidence: 99%

Key Technology of Automation Control Based on Artificial Intelligence Technology

Wang

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure between local frames tends to be inaccurate due to the lack of guidance to force long-range temporal perception; ii) explicit motion learning is usually ignored, leading to partial information loss. To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder. Specifically, the long-short contrastive objective is to endow local frame features with long-form temporal awareness by maximizing their agreement with the global token of videos belonging to the same class. The motion autodecoder is a lightweight architecture to reconstruct pixel motions from the differential features, which explicitly embeds the network with motion dynamics. By this means, MoLo can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching. To demonstrate the effectiveness, we evaluate MoLo on five standard benchmarks, and the results show that MoLo favorably outperforms recent advanced methods. The source code is available at https://github. com/alibaba-mmai-research/MoLo.

show abstract

Relation-Aware Language-Graph Transformer for Question Answering

Park¹,

Choi²,

Ko³

et al. 2023

AAAI

View full text Add to dashboard Cite

Question Answering (QA) is a task that entails reasoning over natural language contexts, and many relevant works augment language models (LMs) with graph neural networks (GNNs) to encode the Knowledge Graph (KG) information. However, most existing GNN-based modules for QA do not take advantage of rich relational information of KGs and depend on limited information interaction between the LM and the KG. To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner. Specifically, QAT constructs Meta-Path tokens, which learn relation-centric embeddings based on diverse structural and semantic relations. Then, our Relation-Aware Self-Attention module comprehensively integrates different modalities via the Cross-Modal Relative Position Bias, which guides information exchange between relevant entities of different modalities. We validate the effectiveness of QAT on commonsense question answering datasets like CommonsenseQA and OpenBookQA, and on a medical question answering dataset, MedQA-USMLE. On all the datasets, our method achieves state-of-the-art performance. Our code is available at http://github.com/mlvlab/QAT.

show abstract

SSAR-GNN: Self-Supervised Artist Recommendation with Graph Neural Networks

Cited by 6 publications

References 14 publications

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

Key Technology of Automation Control Based on Artificial Intelligence Technology

Relation-Aware Language-Graph Transformer for Question Answering

Contact Info

Product

Resources

About