# Mutual Distillation Learning Network for Trajectory-User Linking

arXiv: https://arxiv.org/abs/2205.03773 · HTML: https://mlsanity.com/paper/2205.03773/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 8 May 2022.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [The State of Knowledge Distillation for Classification](https://mlsanity.com/paper/1912.10850/) (2019)
- [Trajectory-Based Spatiotemporal Entity Linking](https://mlsanity.com/paper/2010.01516/) (2020)

## Built on by (most cited first, 15 of 15)

- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era](https://mlsanity.com/paper/2403.14151/) (2024)
- [Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks](https://mlsanity.com/paper/2302.10903/) (2023)
- [TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration](https://mlsanity.com/paper/2410.20445/) (2024)
- [Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning](https://mlsanity.com/paper/2404.14073/) (2024)
- [Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models](https://mlsanity.com/paper/2505.18120/) (2025)
- [PTrajM: Efficient and Semantic-rich Trajectory Learning with Pretrained Trajectory-Mamba](https://mlsanity.com/paper/2408.04916/) (2024)
- [Scalable Trajectory-User Linking with Dual-Stream Representation Networks](https://mlsanity.com/paper/2503.15002/) (2025)
- [Trajectory-User Linking Is Easier Than You Think](https://mlsanity.com/paper/2212.07081/) (2022)
- [GADformer: A Transparent Transformer Model for Group Anomaly Detection on Trajectories](https://mlsanity.com/paper/2303.09841/) (2023)
- [TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model](https://mlsanity.com/paper/2510.17545/) (2025)
- [Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Prediction](https://mlsanity.com/paper/2310.08328/) (2023)
- [Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data](https://mlsanity.com/paper/2504.01979/) (2025)
- [TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond](https://mlsanity.com/paper/2605.06906/) (2026)
- [Multi-Relational Knowledge Graph Enhanced Embedding for Trajectory-User Linking](https://mlsanity.com/paper/2608.08646/) (2026)

## Abstract (arXiv)

Trajectory-User Linking (TUL), which links trajectories to users who generate them, has been a challenging problem due to the sparsity in check-in mobility data. Existing methods ignore the utilization of historical data or rich contextual features in check-in data, resulting in poor performance for TUL task. In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL. Specifically, MainTUL is composed of a Recurrent Neural Network (RNN) trajectory encoder that models sequential patterns of input trajectory and a temporal-aware Transformer trajectory encoder that captures long-term time dependencies for the corresponding augmented historical trajectories. Then, the knowledge learned on historical trajectories is transferred between the two trajectory encoders to guide the learning of both encoders to achieve mutual distillation of information. Experimental results on two real-world check-in mobility datasets demonstrate the superiority of MainTUL against state-of-the-art baselines. The source code of our model is available at https://github.com/Onedean/MainTUL.