Belangrijkste concepten
사전 훈련된 대형 언어 모델을 활용한 TPLLM은 교통 데이터의 복잡한 시공간 의존성을 분석하고 교통 예측 작업에 효과적으로 활용할 수 있음을 입증합니다.
Statistieken
"Experiments on two real-world datasets demonstrate that TPLLM exhibits commendable performance in both full-sample and few-shot prediction scenarios."
"The optimizer of the TPLLM is set as Adam, and the hyperparameters are shown in Table II."
Citaten
"Recognizing the sequential nature of traffic data, similar to language, we introduce TPLLM, a novel traffic prediction framework leveraging LLMs."
"The precision of prevailing deep learning-driven traffic prediction models typically sees an upward trend with a rise in the volume of training data."