# Continual Graph Memory for Adaptive Recommendation under Intent Drift

arXiv: https://arxiv.org/abs/2609.04651 · HTML: https://mlsanity.com/paper/2609.04651/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Neural Attentive Session-based Recommendation](https://mlsanity.com/paper/1711.04725/) (2017)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [Global Context Enhanced Graph Neural Networks for Session-based Recommendation](https://mlsanity.com/paper/2106.05081/) (2021)
- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking](https://mlsanity.com/paper/2311.02089/) (2023)
- [A Survey on LLM-powered Agents for Recommender Systems](https://mlsanity.com/paper/2502.10050/) (2025)
- [Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Network](https://mlsanity.com/paper/2206.12781/) (2022)
- [Large Language Models for Intent-Driven Session Recommendations](https://mlsanity.com/paper/2312.07552/) (2023)
- [A Re-visit of the Popularity Baseline in Recommender Systems](https://mlsanity.com/paper/2005.13829/) (2020)
- [ReLoop: A Self-Correction Continual Learning Loop for Recommender Systems](https://mlsanity.com/paper/2204.11165/) (2022)
- [D2K: Turning Historical Data into Retrievable Knowledge for Recommender Systems](https://mlsanity.com/paper/2401.11478/) (2024)
- [ReLoop2: Building Self-Adaptive Recommendation Models via Responsive Error Compensation Loop](https://mlsanity.com/paper/2306.08808/) (2023)
- [Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation](https://mlsanity.com/paper/2503.05493/) (2025)
- [LLMGreenRec: LLM-Based Multi-Agent Recommender System for Sustainable E-Commerce](https://mlsanity.com/paper/2603.11025/) (2026)

## Abstract (arXiv)

This paper studies adaptive recommendation under intent drift, where feedback from each recommendation outcome can reveal whether the relational evidence used for ranking is useful, missing, or misleading. While Knowledge Graphs (KGs) provide essential semantic structure to handle these shifts, traditional KG-enhanced systems treat the graph as a static retrieval substrate, making it brittle to evolving intents, noisy metadata, and recurring failure patterns. This paper proposes CGM-Rec, a continual graph memory framework for adaptive recommendation. CGM-Rec treats the graph state as a writable memory and maintains two complementary components. Therein, a Semantic Graph Memory is updated conservatively through quality-gated typed operations for storing stable and high-confidence relational knowledge. Meanwhile, an Episodic Lesson Memory acts as a fast reactive memory that learns recent outcomes, failure cases, and corrective hints. During testing, model parameters remain frozen and adaptation occurs only through memory writes. We evaluate CGM-Rec under a frozen-parameter, one-pass reranking protocol, where encoders and prompts remain fixed during testing and adaptation occurs only through memory writes. Experiments across multiple recommendation settings show that CGM-Rec improves over evaluated neural and LLM-based baselines on most metrics. Particularly, under sampled-candidate reranking, CGM-Rec improves HR@1 by up to 29.58% over the strongest LLM baseline on Bundle, and outperforms K-RagRec on metadata-rich ML-100K with HR@5 of 0.5941 versus 0.4746.