ASRA-GNN: ADAPTIVE SIGNED RELATION-AWARE GRAPH NEURAL NETWORK FOR FRIEND RECOMMENDATION

Signed-Graph Recommendation as Structural Consistency Maximization

This work identifies a fundamental inconsistency across the structural, propagation, and semantic layers of existing models that leads to biased representations learned from sparse or noisy datasets, and proposes a unified framework named SSC-Loop that treats signed social recommendation as the maximization of structural consistency.

Explainable Recommendation in Graph Neural Networks Using Propagation Path Analysis and Counterfactual Graph Editing

Graph Neural Networks (GNNs), particularly LightGCN, have achieved strong performance in collaborative filtering-based recommendation systems. However, their black-box nature makes it difficult to explain why specific items are recommended, limiting trust and adoption in user-facing applications. In this paper, we propose a post-hoc explainability framework for LightGCN combining two complementary techniques: Propagation Path Analysis, which decomposes recommendation scores by propagation layer to attribute influence to specific training interactions, and Counterfactual Graph Editing, which identifies the most influential user-item edges through structural sensitivity analysis and targeted edge removal. We evaluate on MovieLens-1M against three baselines including random edge removal, degree-based attribution, and LIME. Our method achieves a mean absolute score drop of 0.0322, representing a 3.02× lift over random, a 1.26× lift over LIME, and a 5.35× lift over degree-based attribution. Faithfulness evaluation against post-fine-tuning ground truth yields Pearson r = 0.536, confirming that structural sensitivity reliably identifies influential edges without model retraining. Layer contribution analysis reveals that LightGCN recommendations are predominantly driven by direct interactions (Layer 0) and 1-hop neighbours (Layer 1), with deeper layers contributing progressively less.

SigFJProp: Lightweight and Scalable Signed Graph Learning via Opinion Dynamics

Learning on signed graphs poses unique challenges due to the presence of both positive and negative links, which represent complex social dynamics such as trust and conflict. While existing signed graph neural networks (SGNNs) have achieved promising results, most rely on deep, multi-hop propagation architectures that suffer from scalability issues. In this work, we revisit message passing from the perspective of opinion dynamics, and propose SigFJProp, a novel and lightweight SGNN framework inspired by the Friedkin–Johnsen model. SigFJProp models signed message propagation as a discrete-time opinion update process, whose equilibrium state admits a closed-form solution involving the signed forest matrix. To make this computation tractable on large-scale graphs, we introduce Expansion Forest Sampling, a linear-time approximation method tailored for signed networks. Our approach decouples neural representation learning from propagation dynamics, enabling efficient and interpretable learning. Experimental results on seven benchmark datasets, including one with over 750K nodes and 10M edges, demonstrate that SigFJProp achieves competitive or superior performance compared to state-of-the-art methods, while significantly reducing computational overhead. The code is available at https://github.com/SunYubo23/SigFJProp.

Graph-based social recommendation with redundant information suppression

Trust and distrust enhanced recommendation algorithm for signed social networks

Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling

Friend recommendation is inherently graph-structured: the relevance of a potential connection depends on multi-hop social context rather than user attributes alone. However, deploying message-passing GNNs on a production-scale social graph with hundreds of millions of users and tens of billions of edges requires addressing numerous modeling and systems challenges. We present a scalable end-to-end GNN ranking system for production social graphs, focusing on two design choices that are critical in this setting: multi-hash ID embeddings and temporal neighbor sampling. Multi-hash embeddings are common for high-cardinality features, but industrial GNN systems typically either ignore trainable IDs or accept full embedding tables, exceeding 200 GB for our graph. We integrate multi-hash as the primary node representation, reducing the ID-embedding table size by more than 98 percent while preserving ranking quality. Temporal neighbor sampling is well understood in principle, but existing implementations scan full adjacency lists, which is a non-starter for users with tens of thousands of friends. We implement timestamp-sorted CSR storage with binary search, reducing the per-node temporal sampling cost from $O(deg(v) + k)$ to $O(\log(deg(v)) + k)$. Beyond these components, we show that this combination scales and yields measurable production impact. On a graph with 194M users and 28B edges, offline ablations isolate each design choice's contribution. In an online A/B test, our system increases friend additions from recommendations by 16 percent and unique friend adders by 11.5 percent over a strong production baseline. We release our framework for distributed training and inference on large temporal graphs.