ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta

• URL: http://arxiv.org/abs/2608.10187v1
• Date: Mon, 10 Aug 2026 20:02:31 GMT
• Title: ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta
• Abstract summary: ConnectionMind is a production-ready recommendation framework for Meta.<n>It integrates the social network structure with large language models to enable scalable, interpretable, and reasoning-aware personalization.<n>It has been deployed in Meta's large-scale recommendation pipeline and has been evaluated through online A/B tests, achieving a 0.43% improvement in video watch time.
• Score: 39.0476353629498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern recommendation systems on social media platforms such as Meta must model complex social relationships, including friendships, group memberships, and creator interactions, alongside massive and heterogeneous content such as text and video. Traditional recommendation models, however, often omit these signals or treat them independently, lacking the reasoning capability to integrate multi-relational context for fine-grained personalization. We present ConnectionMind, a production-ready recommendation framework that tightly integrates the social network structure with large language models (LLMs) to enable scalable, interpretable, and reasoning-aware personalization in Meta. ConnectionMind constructs a heterogeneous graph connecting users, items, friends, groups, and creator pages, and formulates recommendation as a graph reasoning problem: discovering personalized paths from users to candidate items. An LLM-based policy is employed to reason over these graph structures and guide recommendation decisions. To train the system at scale, ConnectionMind adopts a two-stage learning strategy. We first perform supervised fine-tuning (SFT) on large-scale user-item interaction trajectories to initialize the reasoning policy, followed by end-to-end reinforcement learning (RL) to refine the model's ability to reason over social graphs for personalized recommendation. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of ConnectionMind compared to representative baselines. More importantly, ConnectionMind has been deployed in Meta's large-scale recommendation pipeline and has been evaluated through online A/B tests, achieving a 0.43% improvement in video watch time. These results demonstrate measurable real-world impact in a production recommendation system.

Related papers

• Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation [60.03046892817763]
  Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems.<n>Existing methods often struggle to organize and inject complex user-behavioral and item-semantic contexts into recommendation models simultaneously.<n>We propose G2Rec, a scalable framework that unifies holistic graph-based user co-engagement modeling with semantic tokenization for industrial-scale generative recommendation.
  arXiv  Detail & Related papers  (2026-06-18T17:58:32Z)
• Socially Aware Music Recommendation: A Multi-Modal Graph Neural Networks for Collaborative Music Consumption and Community-Based Engagement [0.0]
  This study presents a novel Multi-Modal Graph Neural Network (MM-GNN) framework for socially aware music recommendation.<n>The proposed model introduces a fusion-free deep mutual learning strategy that aligns modality-specific representations from lyrics, audio, and visual data.<n>Emotion-aware embeddings derived from acoustic and textual signals contribute to emotionally aligned recommendations.
  arXiv  Detail & Related papers  (2025-09-13T02:04:39Z)
• Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks [2.86471061970102]
  We propose a hybrid framework integrating large language models (LLMs) and graph neural networks (GNNs)<n>A pre-trained LLM encodes text data (e.g., user reviews) into rich feature vectors, while a heterogeneous user-product graph models interactions and social ties.<n> Experiments on public and real-world financial datasets show our model outperforms standalone LLM or GNN in accuracy, recall, and NDCG, with strong interpretability.
  arXiv  Detail & Related papers  (2025-06-06T08:41:33Z)
• Gated Multimodal Graph Learning for Personalized Recommendation [9.466822984141086]
  Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering.<n>We propose RLMultimodalRec, a lightweight and modular recommendation framework that combines graph-based user modeling with adaptive multimodal item encoding.
  arXiv  Detail & Related papers  (2025-05-30T16:57:17Z)
• SymCERE: Symmetric Contrastive Learning for Robust Review-Enhanced Recommendation [2.087411180679868]
  We propose SymCERE, a contrastive learning method that addresses false negatives in recommendation.<n>Experiments on 15 datasets from three platforms demonstrate that SymCERE outperforms several strong baselines.
  arXiv  Detail & Related papers  (2025-04-03T00:40:09Z)
• APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation [86.29366168836141]
  We propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR) APGL4SR incorporates adaptive and personalized global collaborative information into sequential recommendation systems. As a generic framework, APGL4SR can outperform other baselines with significant margins.
  arXiv  Detail & Related papers  (2023-11-06T01:33:24Z)
• Ordinal Graph Gamma Belief Network for Social Recommender Systems [54.9487910312535]
  We develop a hierarchical Bayesian model termed ordinal graph factor analysis (OGFA), which jointly models user-item and user-user interactions. OGFA not only achieves good recommendation performance, but also extracts interpretable latent factors corresponding to representative user preferences. We extend OGFA to ordinal graph gamma belief network, which is a multi-stochastic-layer deep probabilistic model.
  arXiv  Detail & Related papers  (2022-09-12T09:19:22Z)
• Social Recommendation with Self-Supervised Metagraph Informax Network [21.41026069530997]
  We propose a Self-Supervised Metagraph Infor-max Network (SMIN) which investigates the potential of incorporating social- and knowledge-aware relational structures into the user preference representation for recommendation. To inject high-order collaborative signals, we generalize the mutual information learning paradigm under the self-supervised graph-based collaborative filtering. Experimental results on several real-world datasets demonstrate the effectiveness of our SMIN model over various state-of-the-art recommendation methods.
  arXiv  Detail & Related papers  (2021-10-08T08:18:37Z)
• User Memory Reasoning for Conversational Recommendation [68.34475157544246]
  We study a conversational recommendation model which dynamically manages users' past (offline) preferences and current (online) requests. MGConvRex captures human-level reasoning over user memory and has disjoint training/testing sets of users for zero-shot (cold-start) reasoning for recommendation.
  arXiv  Detail & Related papers  (2020-05-30T05:29:23Z)
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning [74.05478502080658]
  This paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. The proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
  arXiv  Detail & Related papers  (2020-03-15T02:33:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.