1 code implementation • 6 Oct 2023 • Heehyeon Kim, Jinhyeok Choi, Joyce Jiyoung Whang
We address this problem using Graph Neural Networks (GNNs) by proposing a dynamic relation-attentive aggregation mechanism.
1 code implementation • 31 May 2023 • Jaejun Lee, Chanyoung Chung, Joyce Jiyoung Whang
In this paper, we propose an INductive knowledge GRAph eMbedding method, InGram, that can generate embeddings of new relations as well as new entities at inference time.
1 code implementation • 29 May 2023 • Chanyoung Chung, Jaejun Lee, Joyce Jiyoung Whang
By learning compact representations of triplets and qualifiers and feeding them into the transformers, we reduce the computation cost of using transformers.
1 code implementation • 2 May 2023 • Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng, Joyce Jiyoung Whang
Most existing retrieval-augmented language models (LMs) assume a naive dichotomy within a retrieved document set: query-relevance and irrelevance.
1 code implementation • 6 Feb 2023 • Chanyoung Chung, Joyce Jiyoung Whang
We define a bi-level knowledge graph that consists of the base-level and the higher-level triplets.
no code implementations • 24 Apr 2020 • Joyce Jiyoung Whang, Inderjit S. Dhillon
To solve this problem, we propose intuitive objective functions, and develop an an efficient iterative algorithm which we call the NEO-CC algorithm.
no code implementations • 5 Feb 2016 • Yangyang Hou, Joyce Jiyoung Whang, David F. Gleich, Inderjit S. Dhillon
In this paper, we consider two fast multiplier methods to accelerate the convergence of an augmented Lagrangian scheme: a proximal method of multipliers and an alternating direction method of multipliers (ADMM).