8000 DUMoE/README.md at master · idvxlab/DUMoE · GitHub
[go: up one dir, main page]

Skip to content

Latest commit

 

History

History
57 lines (34 loc) · 1.72 KB

README.md

File metadata and controls

57 lines (34 loc) · 1.72 KB

DUMoE

This repository contains the official implementation of DUMoE, proposed in the paper:

Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts

NeurIPS 2026

Overview

DUMoE is a drift-aware multimodal user representation learning framework designed to capture evolving user interests from social media behaviors.

The framework consists of two main components:

  • Temporal Dynamics-Aware Backbone Network: Integrates static user profiles, short-term behavioral patterns, and long-term temporal dependencies to learn comprehensive user representations.
  • Sparse Mixture-of-Experts (MoE) Interest Adapter: Employs expert specialization and adaptive sparse routing to capture diverse user interests and model temporal interest drift.

DUMoE is evaluated on two downstream tasks:

  1. User Interest Classification
  2. User Interaction Prediction

Framework

DUMoE Framework

Dataset

We construct a large-scale multimodal social media dataset from X (formerly Twitter), covering 15 interest domains.

  • 14,015 users
  • 7,685,700 posts
  • 2,890,668 images
  • 15 interest categories

The released dataset contains anonymized user IDs and tweet IDs, with content filtering applied prior to distribution.

Requirements

The implementation is developed with Python and PyTorch.

Installation

git clone <REPOSITORY_URL>
cd DUMoE

conda create -n dumoe python=3.11
conda activate dumoe

pip install -r requirements.txt
0