Transformers with Attentive Federated Aggregation for Time Series Stock Forecasting

Recent innovations in transformers have shown their superior performance in natural language processing (NLP) and computer vision (CV). The ability to capture long-range dependencies and interactions in sequential data has also triggered a great interest in time series modeling, leading to the widespread use of transformers in many time series applications. However, being the most common and crucial application, the adaptation of transformers to time series forecasting has remained limited, with both promising and inconsistent results. In contrast to the …

aggregation computer computer vision cs.ai cs.dc cs.lg data dependencies forecasting innovations interactions language language processing modeling natural natural language natural language processing nlp performance processing q-fin.st series stock time series transformers vision