1 code implementation • 4 Apr 2024 • Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Dong-Kyu Chae
Knowledge Graphs (KGs) have proven essential in information processing and reasoning applications because they link related entities and give context-rich information, supporting efficient information retrieval and knowledge discovery; presenting information flow in a very effective manner.
1 code implementation • 1 Apr 2024 • JaeMin Kim, Yohan Na, KangMin Kim, Sang Rak Lee, Dong-Kyu Chae
However, they neglect to evaluate the quality of their constructed sentiment representations; they just focus on improving the fine-tuning performance, which overshadows the representation quality.
no code implementations • 25 Mar 2024 • Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Serbetar Karlo, Dong-Kyu Chae
CADGL surpasses other state-of-the-art DDI prediction models, excelling in predicting clinically valuable novel DDIs, supported by rigorous case studies.
Ranked #1 on Drug–drug Interaction Extraction on DrugBank
1 code implementation • 3 Mar 2024 • Azmine Toushik Wasi, Šerbetar Karlo, Raima Islam, Taki Hasan Rafi, Dong-Kyu Chae
Complex chemical structures, like drugs, are usually defined by SMILES strings as a sequence of molecules and bonds.
no code implementations • 20 Jan 2024 • Jiahao Nie, Zhiwei He, Xudong Lv, Xueyi Zhou, Dong-Kyu Chae, Fei Xie
Based on this observation, we design a novel point set representation learning network inheriting transformer architecture, termed AdaFormer, which adaptively encodes the dynamically varying shape and size information from cross-category data in a unified manner.
1 code implementation • 2 May 2023 • Azmine Toushik Wasi, Karlo Šerbetar, Raima Islam, Taki Hasan Rafi, Dong-Kyu Chae
We also employ learnable anchor points in the embedding space with label distributions and multi-head self-attention mechanism to optimize performance against weak predictions with reliability balancing, which is a strategy that leverages anchor points, attention scores, and confidence values to enhance the resilience of label predictions.
Ranked #1 on Facial Expression Recognition (FER) on AffWild2