Pünktlich zur derzeit in Hannover stattfindenden 18. ACM International Conference on #WebSearch and #DataMining (#WSDM2025) erklärt Prof. Dr. Maria-Esther Vidal, Leiterin der @TIB_SDM, im #TIBBlog, was den #LeibnizDataManager einzigartig macht und warum Forschende ihn nutzen sollten: https://blog.tib.eu/2025/03/10/leibniz-data-manager-ldm-wie-sich-forschungsdaten-effektiv-managen-lassen
#Forschungsdaten #Forschungsdatenmanagement #WSDM
Leibniz Data Manager (LDM): Wie sich Forschungsdaten effektiv managen lassen - TIB-Blog
Wissenschaftliche Entdeckungen basieren auf gut strukturierten, leicht zugänglichen und wiederverwendbaren Forschungsdaten. Forschende stehen jedoch häufig vor Herausforderungen wie nicht miteinander verbundenen Datensätzen, inkonsistenten Metadaten und zeitaufwändiger Datenaufbereitung. Der Leibniz Data Manager (LDM) bietet eine leistungsstarke, FAIR-konforme Plattform für das Forschungsdatenmanagement. Durch die Nutzung von Wissensgraphen (Knowledge Graphs, KGs) strukturiert und verknüpft der LDM Forschungsdaten, sodass sie auffindbar, zugänglich, interoperabel und wiederverwendbar (FAIR) sind.
I’ve been in Seattle this week for
#SIGSPATIAL to present our paper ‘Leveraging Language Foundation Models for Human Mobility Forecasting’ in which we used
#llm with mobility prompts for human mobility forecasting. The SIGSPATIAL paper
https://arxiv.org/abs/2209.05479 is a follow up of our earlier
#NLG paper for time-series forecasting at
#WSDM 2022
https://dl.acm.org/doi/abs/10.1145/3488560.3498387. More to come on this!
Departing back to Sydney tomorrow.
#AI #ML #spatiotemporal #forecasting
Leveraging Language Foundation Models for Human Mobility Forecasting
In this paper, we propose a novel pipeline that leverages language foundation
models for temporal sequential pattern mining, such as for human mobility
forecasting tasks. For example, in the task of predicting Place-of-Interest
(POI) customer flows, typically the number of visits is extracted from
historical logs, and only the numerical data are used to predict visitor flows.
In this research, we perform the forecasting task directly on the natural
language input that includes all kinds of information such as numerical values
and contextual semantic information. Specific prompts are introduced to
transform numerical temporal sequences into sentences so that existing language
models can be directly applied. We design an AuxMobLCast pipeline for
predicting the number of visitors in each POI, integrating an auxiliary POI
category classification task with the encoder-decoder architecture. This
research provides empirical evidence of the effectiveness of the proposed
AuxMobLCast pipeline to discover sequential patterns in mobility forecasting
tasks. The results, evaluated on three real-world datasets, demonstrate that
pre-trained language foundation models also have good performance in
forecasting temporal sequences. This study could provide visionary insights and
lead to new research directions for predicting human mobility.
Sptoify announced its new Data Science Challenge
Spotify Sequential Skip Prediction Challenge is a part of #WSDM Cup 2019. The dataset comprises 130M Spotify listening sessions, and the task is to predict if a track is skipped. The challenge is live today, and runs until Jan 4.
https://www.crowdai.org/challenges/spotify-sequential-skip-prediction-challenge
Nobody wants to join?
crowdAI
Fighting for Open Science with Open Data
TIB
Flora Salim
imuhammad