The recent success of Transformer has benefited many real-world applications, with its capability of building long dependency through pairwise dot-products. However, the strong assumption that elements are directly attentive to each other limits the performance of tasks with high-order dependencies such as natural language understanding and Image captioning. To solve such problems, we are the first to define the Jump Self-attention (JAT) to build Transformers. Inspired by the pieces moving of English Draughts, we introduce the spectral convolutional technique to calculate JAT on the dot-product feature map. This technique allows JAT's propagation in each self-attention head and is interchangeable with the canonical self-attention. We further develop the higher-order variants under the multi-hop assumption to increase the generality. Moreover, the proposed architecture is compatible with the pre-trained models. With extensive experiments, we empirically show that our methods significantly increase the performance on ten different tasks.

Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, including quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a ProbSparse self-attention mechanism, which achieves O(L log L) in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.

The Transformer model has benefited various real-world applications, where the self-attention mechanism with dot-products shows superior alignment ability on building long dependency. However, the pair-wisely attended self-attention limits further performance improvement on challenging tasks. To the extent of our knowledge, this is the first work to define the Triplet Attention (A3) for Transformer, which introduces triplet connections as the complementary dependency. Specifically, we define the triplet attention based on the scalar triplet product, which may be interchangeably used with the canonical one within the multi-head attention. It allows the self-attention mechanism to attend to diverse triplets and capture complex dependency. Then, we utilize the permuted formulation and kernel tricks to establish a linear approximation to A3. The proposed architecture could be smoothly integrated into the pre-training by modifying head configurations. Extensive experiments show that our methods achieve significant performance improvement on various tasks and two benchmarks.

The spatial-temporal modeling on long sequences is of great importance in many real-world applications. Recent studies have shown the potential of applying the self-attention mechanism to improve capturing the complex spatial-temporal dependencies. However, the lack of underlying structure information weakens its general performance on long sequence spatial-temporal problem. To overcome this limitation, we proposed a novel method, named the Proximity-aware Long Sequence Learning framework, and apply it to the spatial-temporal forecasting task. The model substitutes the canonical self-attention by leveraging the proximity-aware attention, which enhances local structure clues in building long-range dependencies with a linear approximation of attention scores. The relief adjacency matrix technique can utilize the historical global graph information for consistent proximity learning. Meanwhile, the reduced decoder allows for fast inference in a non-autoregressive manner. Extensive experiments are conducted on five large-scale datasets, which demonstrate that our method achieves state-of-the-art performance and validates the effectiveness brought by local structure information.