Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Xie, Xike"'
Detecting Out-of-Distribution (OOD) inputs is crucial for improving the reliability of deep neural networks in the real-world deployment. In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method th
Externí odkaz:
http://arxiv.org/abs/2410.07617
Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding phases. Althoug
Externí odkaz:
http://arxiv.org/abs/2409.12490
Although Large Language Models (LLMs) have demonstrated potential in processing graphs, they struggle with comprehending graphical structure information through prompts of graph description sequences, especially as the graph size increases. We attrib
Externí odkaz:
http://arxiv.org/abs/2409.03258
Large Language Models have excelled in various fields but encounter challenges in memory and time efficiency due to the expanding Key-Value (KV) cache required for long-sequence inference. Recent efforts try to reduce KV cache size to a given memory
Externí odkaz:
http://arxiv.org/abs/2407.11550
In the realm of distributed systems tasked with managing and processing large-scale graph-structured data, optimizing graph partitioning stands as a pivotal challenge. The primary goal is to minimize communication overhead and runtime cost. However,
Externí odkaz:
http://arxiv.org/abs/2402.18304
When deploying a trained machine learning model in the real world, it is inevitable to receive inputs from out-of-distribution (OOD) sources. For instance, in continual learning settings, it is common to encounter OOD samples due to the non-stationar
Externí odkaz:
http://arxiv.org/abs/2401.11726
Interactive data exploration (IDE) is an effective way of comprehending big data, whose volume and complexity are beyond human abilities. The main goal of IDE is to discover user interest regions from a database through multi-rounds of user labelling
Externí odkaz:
http://arxiv.org/abs/2212.03423
Recently, research communities highlight the necessity of formulating a scalability continuum for large-scale graph processing, which gains the scale-out benefits from distributed graph systems, and the scale-up benefits from high-performance acceler
Externí odkaz:
http://arxiv.org/abs/2203.13005
Graph partitioning plays a vital role in distributedlarge-scale web graph analytics, such as pagerank and labelpropagation. The quality and scalability of partitioning strategyhave a strong impact on such communication- and computation-intensive appl
Externí odkaz:
http://arxiv.org/abs/2201.00472
The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such as urban
Externí odkaz:
http://arxiv.org/abs/2102.06027