A Sample-driven Selection Framework: Towards Graph Contrastive Networks with Reinforcement Learning

Xiangping Zheng, Xiuxin Hao, Bo Wu, Xigang Bao, Xuan Zhang, Wei Li, Xun Liang

Abstract: Graph Contrastive Learning (GCL) applied in real-world scenarios aims to alleviate label scarcity by harnessing graph structures to disseminate labels from a limited set of labeled data to a broad spectrum of unlabeled data. Recent advancements in amalgamating neural network capabilities with graph structures have demonstrated promising progress. However, prevalent GCL methodologies often overlook the fundamental issue of semi-supervised learning (SSL), relying on uniform negative sample selection schemes such as random sampling, thus yielding suboptimal performance within contexts. To address this challenge, we present GraphSaSe, a tailored approach designed specifically for graph representation tasks. Our model consists of two pivotal components: a Graph Contrastive Learning Framework (GCLF) and a Selection Distribution Generator (SDG) propelled by reinforcement learning to derive selection probabilities. We introduce an innovative strategy whereby the divergence between positive graph representations is translated into a reward mechanism, dynamically guiding the selection of negative samples during training. This adaptive methodology aims to minimize the divergence between augmented positive pairs, thereby enriching graph representation learning crucial for applications. Comprehensive experimentation across diverse real-world datasets validates the effectiveness of our algorithm, positioning it favorably against contemporary state-of-the-art methodologies.

Primary Subject Area: [Generation] Social Aspects of Generative AI

Secondary Subject Area: [Engagement] Emotional and Social Signals

Relevance To Conference: This work advances multimedia/multimodal processing through GraphSaSe, which couples Graph Contrastive Learning Framework (GCLF) with a Selection Distribution Generator (SDG). Enhanced feature learning from GraphSaSe facilitates precise multimedia content classification and retrieval. Its optimized fusion of multimodal data augments performance across video, text, and audio analytics. In societal aspects of artificial intelligence, GraphSaSe aids in social network analysis and public health monitoring, bolstering an understanding of societal dynamics and supporting disease control strategies. Regarding social signals, GraphSaSe's improved graph representations enable better comprehension of emotional tendencies and predictions of social interactions, enhancing sentiment analysis and behavioral forecasting. Hence, this work contributes significantly to the development of AI applications in social analytics, underscoring the potential of GraphSaSe in both technical and societal domains.

Submission Number: 1363