As a cost-effective alternative, learning-free PTQ schemes have been proposed. However, the performance is somewhat limited because they cannot consider the inter-layer dependency within the attention module, which is a significant feature of Transformers. In this paper, we thus propose a novel PTQ algorithm that balances accuracy and efficiency. The key idea of the proposed algorithm called aespa is to perform quantization layer-wise for efficiency while targeting attention-wise reconstruction to consider the cross-layer dependency.

Unsupervised Graph Domain Adaptation (UGDA) involves the transfer of knowledge from a label-rich source graph to an unlabeled target graph under domain discrepancies. Despite the proliferation of methods designed for this emerging task, the lack of standard experimental settings and fair performance comparisons makes it challenging to understand which and when models perform well across different scenarios.

In addition to sequence-based approaches, structure-based encoders have emerged to leverage the 3D structural information of proteins.

We further design an expert-wise training strategy to alleviate the impact of unhelpful demonstrations when optimizing the retriever model.

Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model.