FLAG: Towards Graph Query Autocompletion for Large Graphs

Yi, Peipei; Li, Jianping; Choi, Byron; Bhowmick, Sourav S.; Xu, Jianliang

doi:10.1007/s41019-022-00182-8

Cited by 10 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, many recent works (Ho, Jain, and Abbeel 2020;Song, Meng, and Another way to accelerate diffusion models is reducing computation by exploiting the sparsity of the input data or the model parameters. There are several techniques (Dong et al 2017;Liu et al 2018;Ren et al 2018;Liu et al 2019;Child et al 2019;Bolya et al 2023;Han et al 2023;Bi et al 2023;Zhang et al 2023;Yi et al 2022) available for implementing sparse computation. However, directly applying existing techniques such as tiled sparse convolution (Ren et al 2018) fails to achieve considerable speedup and image quality in our scenario.…”

Section: Diffusion Model Accelerationmentioning

confidence: 99%

Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference

Yu,

Li,

et al. 2024

AAAI

View full text Add to dashboard Cite

Due to the recent success of diffusion models, text-to-image generation is becoming increasingly popular and achieves a wide range of applications. Among them, text-to-image editing, or continuous text-to-image generation, attracts lots of attention and can potentially improve the quality of generated images. It's common to see that users may want to slightly edit the generated image by making minor modifications to their input textual descriptions for several rounds of diffusion inference. However, such an image editing process suffers from the low inference efficiency of many existing diffusion models even using GPU accelerators. To solve this problem, we introduce Fast Image Semantically Edit (FISEdit), a cached-enabled sparse diffusion model inference engine for efficient text-to-image editing. The key intuition behind our approach is to utilize the semantic mapping between the minor modifications on the input text and the affected regions on the output image. For each text editing step, FISEdit can 1) automatically identify the affected image regions and 2) utilize the cached unchanged regions' feature map to accelerate the inference process. For the former, we measure the differences between cached and ad hoc feature maps given the modified textual description, extract the region with significant differences, and capture the affected region by masks. For the latter, we develop an efficient sparse diffusion inference engine that only computes the feature maps for the affected region while reusing the cached statistics for the rest of the image. Finally, extensive empirical results show that FISEdit can be 3.4 times and 4.4 times faster than existing methods on NVIDIA TITAN RTX and A100 GPUs respectively, and even generates more satisfactory images.

show abstract

Section: Diffusion Model Accelerationmentioning

confidence: 99%

Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference

Yu,

Li,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…In the domains of natural language understanding [1] and knowledge inference [2,3], a comprehensive KG offers significant performance improvements as prior knowledge for downstream tasks such as question answering [4] and recommendation systems [5,6]. However, real-world KGs often represent only a subset of the complete KG, containing a vast amount of undiscovered and poorly organized potential knowledge that is valuable for deep mining and analysis, including node classification [7], node clustering [8], graph query [9][10][11], entity recognition [12], and link prediction [13]. Consequently, efficient KG representation has become a critical challenge.…”

Section: Introductionmentioning

confidence: 99%

RiQ-KGC: Relation Instantiation Enhanced Quaternionic Attention for Complex-Relation Knowledge Graph Completion

Wang,

Ning,

Jiang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

A knowledge graph is a structured semantic network designed to describe physical entities and relations in the world. A comprehensive and accurate knowledge graph is essential for tasks such as knowledge inference and recommendation systems, making link prediction a popular problem for knowledge graph completion. However, existing approaches struggle to model complex relations among entities, which severely hampers their ability to complete knowledge graphs effectively. To address this challenge, we propose a novel hierarchical multi-head attention network embedding framework, called RiQ-KGC, which integrates different-grained contextual information of knowledge graph triples and models quaternion rotation relations between entities. Furthermore, we propose a relation instantiation method for alleviating the difficulty of expressing complex relations between entities. To enhance the expressiveness of relation representation, the relation is integrated by Transformer to obtain multi-hop neighbor information, so that one relation can be embedded into different embeddings according to different entities. Experimental results on four datasets demonstrate that RiQ-KGC exhibits strong competitiveness compared to state-of-the-art models in link prediction, while the ablation experiments reveal that the proposed relation instantiation method achieves great performance.

show abstract