# Which Matters Most in Making Fund Investment Decisions? A Multi-granularity Graph Disentangled Learning Framework

arXiv: https://arxiv.org/abs/2311.13864 · HTML: https://mlsanity.com/paper/2311.13864/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 23 Nov 2023.

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

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Heterogeneous Information Network Embedding for Recommendation](https://mlsanity.com/paper/1711.10730/) (2017)
- [Disentangled Graph Collaborative Filtering](https://mlsanity.com/paper/2007.01764/) (2020)
- [Multi-Interest Network with Dynamic Routing for Recommendation at Tmall](https://mlsanity.com/paper/1904.08030/) (2019)
- [A Survey on Session-based Recommender Systems](https://mlsanity.com/paper/1902.04864/) (2019)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning](https://mlsanity.com/paper/2110.02027/) (2021)
- [Knowledge Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2205.00976/) (2022)
- [Graph Trend Filtering Networks for Recommendations](https://mlsanity.com/paper/2108.05552/) (2021)
- [CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space](https://mlsanity.com/paper/2204.11067/) (2022)
- [Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System](https://mlsanity.com/paper/2204.08807/) (2022)
- [Facial Expression Analysis under Partial Occlusion: A Survey](https://mlsanity.com/paper/1802.08784/) (2018)
- [When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation](https://mlsanity.com/paper/2205.01286/) (2022)
- [Unify Local and Global Information for Top-N Recommendation](https://mlsanity.com/paper/2012.01635/) (2020)

## Built on by (most cited first, 2 of 2)

- [Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data](https://mlsanity.com/paper/2412.03913/) (2024)
- [Who Is Lagging Behind: Profiling Student Behaviors with Graph-Level Encoding in Curriculum-Based Online Learning Systems](https://mlsanity.com/paper/2508.18925/) (2025)

## Abstract (arXiv)

In this paper, we highlight that both conformity and risk preference matter in making fund investment decisions beyond personal interest and seek to jointly characterize these aspects in a disentangled manner. Consequently, we develop a novel M ulti-granularity Graph Disentangled Learning framework named MGDL to effectively perform intelligent matching of fund investment products. Benefiting from the well-established fund graph and the attention module, multi-granularity user representations are derived from historical behaviors to separately express personal interest, conformity and risk preference in a fine-grained way. To attain stronger disentangled representations with specific semantics, MGDL explicitly involve two self-supervised signals, i.e., fund type based contrasts and fund popularity. Extensive experiments in offline and online environments verify the effectiveness of MGDL.