2026· ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)· Vol 12, pp. 1108-1116· 0 citations
TL;DR
A post-hoc explainability framework for LightGCN is proposed 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.
Abstract
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.
ASRA-GNN addresses gaps in Signed Graph Neural Networks through three contributions: Sign-Aware Structural Role Attention grounded in four social network theories, a Locally Adaptive Theory Mixing gate replacing TrustSGCN's binary global threshold with a continuous per-node end-toend learned mixing function, and a Signed Contrastive Recommendation Loss providing the first ranking objective for signed user-user graphs.
Pharsana Parveen M, Stanis Arul Mary A· International journal of Com...· 0 citations
Explainable recommendation has been conceptualized as a joint ranking task encompassing both items and explanations within contemporary recommender system research. The modeling of user–item–explanation triplets can be effectively facilitated by Graph Neural Networks (GNNs) due to their powerful representation learning capabilities. However, various observable and unobservable confounding factors, such as the user’s mood at the time of purchase and product popularity, may cause users to make decisions that diverge from their genuine preferences. These confounding variables significantly affect GNN models, resulting in inconsistent or inaccurate representations of the relationships among users, items, and explanations. To address these challenges, we propose Causality-enhanced Graph Contrastive Learning for Explainable Recommendation (CGCLER). This method enables item–explanation joint ranking by distinguishing causal and confounding features at the graph-node representation level. Guided by the backdoor adjustment principle, CGCLER further introduces a backdoor-inspired graph contrastive learning objective that constructs representation-level perturbation views by combining causal features with randomly sampled confounding features, thereby encouraging representations that are less affected by varying confounding contexts. The effectiveness of CGCLER is evaluated through experiments on three publicly available datasets.
Graph Collaborative Filtering (GCF) has become the dominant paradigm in modern recommender systems by modeling user-item interactions as a bipartite graph and propagating embeddings through a fixed number of message-passing layers. However, applying a uniform propagation depth to every node ignores a fundamental property of real interaction graphs: nodes differ substantially in their local connectivity, so peripheral nodes quickly suffer from over-smoothing while hub-like nodes remain under-explored beyond their immediate neighborhood. In this paper, we revisit GCF from a tree-structured perspective and propose Neural Tree Collaborative Filtering (NTCF), a framework that re-interprets each node's local neighborhood as a rooted tree and assigns a node-specific propagation depth based on a closed-form local-degree-imbalance score that serves as a discrete Ricci-curvature proxy. We provide a theoretical analysis showing that (i) NTCF strictly generalizes NGCF, degenerating to NGCF when all curvature-induced depth adjustments vanish (a lower bound on its representation power), and (ii) the curvature-aware schedule retains strictly more discriminative information at deep layers on positively-curved (peripheral) nodes than uniform-depth propagation. NTCF can achieve higher performance than most widely used GCF backbone models and can be integrated into existing advanced self-supervised models as a backbone, replacing their original backbone to achieve enhanced performance. Extensive experiments on three public datasets demonstrate the superiority of NTCF.
Jinfeng Xu, Zheyu Chen, Ziyue Peng et al.· 0 citations
Graph-based recommender systems (GBRs) have achieved remarkable success by leveraging Graph Neural Networks (GNNs) to model complex user-item interactions and structural relationships. However, they still face major challenges in real-world environments, including out-of-distribution (OOD) generalization, dynamic user preferences, fairness, and interpretability. These limitations largely arise because conventional GNN-based recommenders rely on correlation-driven learning over observational interaction graphs, often capturing unstable or spurious associations rather than underlying causal mechanisms. Fortunately, causal learning provides a principled framework for modeling the data-generating process and identifying stable causal relationships across environments. By incorporating causal graphs, Structural Causal Models (SCMs), interventions, causal effect estimation, and counterfactual reasoning, it enables the development of more robust, adaptive, fair, and interpretable GBRs. This survey reviews causal learning in GBRs by summarizing key challenges, establishing connections between causal inference and graph neural networks, and presenting a challenge-oriented taxonomy of representative causal techniques. We further review evaluation metrics, benchmark datasets, graph construction protocols, and open-source libraries, and discuss current limitations and future research directions. Overall, this survey provides a systematic overview of causal learning in GBRs and aims to support the development of more robust and trustworthy GBRs.
Counterfactual explanations for graph-structured data seek to determine minimal and realistic modifications required in an input graph to alter a model's prediction to a predefined output. Although counterfactual explainers that support modifying the graph by both adding and removing edges have recently emerged, there is still a lack of general and efficient methods, especially when considering the quality of the generated explanations. Moreover, the problem remains far from solved, as existing methods exhibit different strengths and weaknesses, often trading off between explanation size, coverage and quality. For this reason, it is important to identify where each method performs well and where it falls short, so as to guide future research in the field. Thus, our study compares six state-of-the-art (SOTA) models on a diverse set of real-world and synthetic datasets, covering both binary and multi-class graph and node classification tasks, and evaluates their performance using diverse quantitative and qualitative metrics.
Maria Myrto Villia, Filippos Gouidis, T. Patkos et al.· 0 citations
This work proposes a flexible two-stage diffusion framework that combines graph coarsening with multi-step label propagation in the telecommunications domain and demonstrates that this coarsening-driven approach delivers an optimal balance between scalability, latency, and recommendation quality.
Alessandro Sbandi, F. Siciliano, Fabrizio Silvestri· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
