Quaternion neural networks are parameter-efficient and model multidimensional dependencies by representing four related features as a single entity. However, existing quaternion self-attention computes component-wise scores and applies independent softmax operations to each component, which increases the computational cost and allows attention distributions to diverge across components. We propose a shared-score quaternion self-attention mechanism that computes a single real-valued score using the quaternion inner product and applies a shared attention distribution across all components. This reduces score-computation multiplications by 75% and the number of softmax operations from four to one. We prove that, when queries and keys are produced by quaternion linear projections that induce component pre-mixing, the component-wise and shared scores lie in the same interaction subspace, indicating that independent component-wise attention primarily re-parameterizes the same interactions rather than expanding the feature interaction space. In speech enhancement, our method reduces inference time by up to 44.3% on a GPU and 58.1% on a CPU while maintaining quality, with consistent trends across vision and natural language processing.

The majority of existing multimodal sequential learning methods focus on how to obtain powerful individual representations and neglect to effectively capture the multimodal joint representation. Bilinear attention network (BAN) is a commonly used integration method, which leverages tensor operations to associate the features of different modalities. However, BAN has a poor compatibility for more modalities, since the computational complexity of the attention map increases exponentially with the number of modalities. Based on this concern, we propose a new method called generalizable multi-linear attention network (MAN), which can associate more modalities in acceptable complexity with hierarchical approximation decomposition. Specifically, considering the fact that softmax attention kernels cannot be decomposed as linear operation directly, we adopt the addition random features mechanism to approximate the non-linear softmax functions with enough theoretical analysis. Furthermore, we also introduce the local sequential constraints, which can be combined with ARF conveniently, as positional information. We conduct extensive experiments on several datasets of corresponding tasks, the experimental results show that MAN could achieve competitive results compared with baseline methods, showcasing the effectiveness of our contributions.

Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore the nature of prompt generalization on unknown domains, we conduct pilot experiments and find that (i) Prompts gaining more attention weight from PLMs' deep layers are more generalizable and (ii) Prompts with more stable attention distributions in PLMs' deep layers are more generalizable. Thus, we offer a fresh objective towards domain-generalizable prompts optimization named ''Concentration'', which represents the ''lookback'' attention from the current decoding token to the prompt tokens, to increase the attention strength on prompts and reduce the fluctuation of attention distribution.We adapt this new objective to popular soft prompt and hard prompt optimization methods, respectively. Extensive experiments demonstrate that our idea improves comparison prompt optimization methods by 1.42% for soft prompt generalization and 2.16% for hard prompt generalization in accuracy on the multi-source domain generalization setting, while maintaining satisfying in-domain performance. The promising results validate the effectiveness of our proposed prompt optimization objective and provide key insights into domain-generalizable prompts.

Attention networks in multimodal learning provide an efficient way to utilize given visual information selectively. However, the computational cost to learn attention distributions for every pair of multimodal input channels is prohibitively expensive. To solve this problem, co-attention builds two separate attention distributions for each modality neglecting the interaction between multimodal inputs. In this paper, we propose bilinear attention networks (BAN) that find bilinear attention distributions to utilize given vision-language information seamlessly. BAN considers bilinear interactions among two groups of input channels, while low-rank bilinear pooling extracts the joint representations for each pair of channels. Furthermore, we propose a variant of multimodal residual networks to exploit eight-attention maps of the BAN efficiently. We quantitatively and qualitatively evaluate our model on visual question answering (VQA 2.0) and Flickr30k Entities datasets, showing that BAN significantly outperforms previous methods and achieves new state-of-the-arts on both datasets.

WefirstclusterthequeriesQusingtheK-means clustering to outputS which indicates the membership of queries to different clusters. The lower half of the figure shows the new valueˆVt computed by sparse dot-products with the keysK and values V corresponding tothe the top-k keys inT. Figure 6: We show training/validation loss convergence for different transformer variants. Both the clustered variants are have a significantly better convergence than bothlsh-1 and lsh-4. Note that due to a smaller batch sizefullmakesmanymoreupdates than allother transformer variants. In figure 6a, we show the training loss convergence for different transformer variants.

Clustered attention makes use of similarities between queries and groups them in order to reduce the computational cost. In particular, we perform fast clustering using locality-sensitive hashing and K-Means and only compute the attention once per cluster.

We collected about 30 million text-image pairs from multiple channels, and built a 2.5TB new dataset (after tokenization, the size becomes about 250GB). The sources of data are basically classified into the following categories: (1) Professional image websites (both English and Chinese). The images in the websites are usually with captions. We have already introduced tokenizers in section 2.2, and here are some details. Colored grids are all the tokens attended to by the token marked "O".