Benjamin Fankhauser

Benjamin Fankhauser

Auto-generated profile, based on publicly available information

Benjamin Fankhauser

University of Bern

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 September 2023 in ACM Transactions on Intelligent Systems and Technology
Verified
Journal Article
Open access
BDBangchao Deng
Bangchao Deng
DYDingqi Yang
Dingqi Yang
BQBingqing Qu
Bingqing Qu
BFBenjamin Fankhauser
Benjamin Fankhauser
PCPhilippe Cudre-Mauroux
Philippe Cudre-Mauroux
As a fundamental problem in human mobility modeling, location prediction forecasts a user’s next location based on historical user mobility trajectories. Recurrent neural networks (RNNs) have been widely used to capture sequential patterns of user visited locations for solving location prediction problems. Due to the sparse nature of real-world user mobility trajectories, existing techniques strive to improve RNNs by incorporating spatiotemporal contexts into the recurrent hidden state passing process of RNNs using context-parameterized transition matrices or gates. However, such a scheme mismatches universal spatiotemporal mobility laws and thus cannot fully benefit from rich spatiotemporal contexts encoded in user mobility trajectories. Against this background, we propose Flashback++, a general RNN architecture designed for modeling sparse user mobility trajectories. It not only leverages rich spatiotemporal contexts to search past hidden states with high predictive power but also learns to optimally combine them via a hidden state re-weighting mechanism, which significantly improves the robustness of the models against different settings and datasets. Our extensive evaluation compares Flashback++ against a sizable collection of state-of-the-art techniques on two real-world location-based social networks datasets and one on-campus mobility dataset. Results show that Flashback++ not only consistently and significantly outperforms all baseline techniques by 20.56% to 44.36% but also achieves better robustness of location prediction performance against different model settings (different RNN architectures and numbers of hidden states to flash back), different levels of trajectory sparsity, and different train-testing splitting ratios than baselines, yielding an improvement of 31.05% to 94.60%.

24 August 2023
Verified
Book Chapter
Closed access
PDF file
BFBenjamin Fankhauser
Benjamin Fankhauser
VBVidushi Bigler
Vidushi Bigler
KRKaspar Riesen
Kaspar Riesen

31 January 2025
Verified
Book Chapter
Closed access
PDF file
BFBenjamin Fankhauser
Benjamin Fankhauser
VBVidushi Bigler
Vidushi Bigler
KRKaspar Riesen
Kaspar Riesen

19 September 2024
Verified
Book Chapter
Closed access
PDF file
BFBenjamin Fankhauser
Benjamin Fankhauser
VBVidushi Bigler
Vidushi Bigler
KRKaspar Riesen
Kaspar Riesen

3 August 2026
Verified
Book Chapter
Closed access
LJLinlin Jia
Linlin Jia
BFBenjamin Fankhauser
Benjamin Fankhauser
VBVidushi Bigler
Vidushi Bigler
KRKaspar Riesen
Kaspar Riesen

8 June 2025
Verified
Book Chapter
Closed access
PDF file
BFBenjamin Fankhauser
Benjamin Fankhauser
VBVidushi Bigler
Vidushi Bigler
KRKaspar Riesen
Kaspar Riesen