no code implementations • 22 Apr 2024 • Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, Alon Benhaim, Misha Bilenko, Johan Bjorck, Sébastien Bubeck, Martin Cai, Caio César Teodoro Mendes, Weizhu Chen, Vishrav Chaudhary, Parul Chopra, Allie Del Giorno, Gustavo de Rosa, Matthew Dixon, Ronen Eldan, Dan Iter, Amit Garg, Abhishek Goswami, Suriya Gunasekar, Emman Haider, Junheng Hao, Russell J. Hewett, Jamie Huynh, Mojan Javaheripi, Xin Jin, Piero Kauffmann, Nikos Karampatziakis, Dongwoo Kim, Mahoud Khademi, Lev Kurilenko, James R. Lee, Yin Tat Lee, Yuanzhi Li, Chen Liang, Weishung Liu, Eric Lin, Zeqi Lin, Piyush Madan, Arindam Mitra, Hardik Modi, Anh Nguyen, Brandon Norick, Barun Patra, Daniel Perez-Becker, Thomas Portet, Reid Pryzant, Heyang Qin, Marko Radmilac, Corby Rosset, Sambudha Roy, Olatunji Ruwase, Olli Saarikivi, Amin Saied, Adil Salim, Michael Santacroce, Shital Shah, Ning Shang, Hiteshi Sharma, Xia Song, Masahiro Tanaka, Xin Wang, Rachel Ward, Guanhua Wang, Philipp Witte, Michael Wyatt, Can Xu, Jiahang Xu, Sonali Yadav, Fan Yang, ZiYi Yang, Donghan Yu, Chengruidong Zhang, Cyril Zhang, Jianwen Zhang, Li Lyna Zhang, Yi Zhang, Yue Zhang, Yunan Zhang, Xiren Zhou
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
no code implementations • 11 Mar 2024 • Moonjeong Park, Jaeseung Heo, Dongwoo Kim
Graph Neural Network (GNN) resembles the diffusion process, leading to the over-smoothing of learned representations when stacking many layers.
no code implementations • 10 Mar 2024 • Shouheng Li, Dongwoo Kim, Qing Wang
In this work, we propose to study the generalization of GNNs through a novel perspective - analyzing the entropy of graph homomorphism.
1 code implementation • 10 Mar 2024 • Shouheng Li, Dongwoo Kim, Qing Wang
Specifically, we propose a new vertex colouring scheme and demonstrate that classical search algorithms can efficiently compute graph representations that extend beyond the 1-WL.
1 code implementation • 9 Oct 2023 • Juntae Kim, Eunjung Cho, Dongwoo Kim, Dongbin Na
Moreover, we also consider predicting the difficulty levels of algorithm problems, which can be used as useful guidance to calculate the required time to solve that problem.
1 code implementation • 22 Aug 2023 • Dain Kim, Jinhyeok Park, Dongwoo Kim
Popularity bias is a widespread problem in the field of recommender systems, where popular items tend to dominate recommendation results.
no code implementations • 2 Jun 2023 • Jaeseung Heo, Seungbeom Lee, Sungsoo Ahn, Dongwoo Kim
Graph-based models have become increasingly important in various domains, but the limited size and diversity of existing graph datasets often limit their performance.
1 code implementation • 30 May 2023 • Yunhui Jang, Dongwoo Kim, Sungsoo Ahn
Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis.
1 code implementation • ICCV 2023 • Minjong Lee, Dongwoo Kim
We analyze the current practices and provide a new guideline for measuring the robustness of purification methods against adversarial attacks.
no code implementations • 10 Mar 2023 • Saemi Moon, Seunghyuk Cho, Dongwoo Kim
We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs.
1 code implementation • 12 Feb 2023 • Moonjeong Park, Youngbin Choi, Namhoon Lee, Dongwoo Kim
Learning dynamical systems is a promising avenue for scientific discoveries.
2 code implementations • 24 Oct 2022 • Jinhyeok Park, Dain Kim, Dongwoo Kim
Our proposed system is based on an ensemble between an item-based variational auto-encoder (VAE) and a Bayesian personalized ranking matrix factorization (BPRMF).
no code implementations • 15 Oct 2022 • Jiye Kim, Seungbeom Lee, Dongwoo Kim, Sungsoo Ahn, Jaesik Park
Designing a neural network architecture for molecular representation is crucial for AI-driven drug discovery and molecule design.
1 code implementation • NeurIPS 2023 • Seunghyuk Cho, Juyong Lee, Dongwoo Kim
We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose latent space consists of a set of Gaussian distributions.
no code implementations • 6 Jun 2022 • Shouheng Li, Dongwoo Kim, Qing Wang
While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs.
Ranked #27 on Node Classification on Actor
no code implementations • 31 May 2022 • Youngsik Yoon, Jinhwan Nam, Hyojeong Yun, Jaeho Lee, Dongwoo Kim, Jungseul Ok
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model.
1 code implementation • 30 May 2022 • Moon Jeong Park, Jungseul Ok, Yo-Seb Jeon, Dongwoo Kim
There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unseen symbols.
no code implementations • 28 May 2022 • Zhenyue Qin, Pan Ji, Dongwoo Kim, Yang Liu, Saeed Anwar, Tom Gedeon
Skeleton sequences are compact and lightweight.
1 code implementation • 25 May 2022 • Seunghyuk Cho, Juyong Lee, Jaesik Park, Dongwoo Kim
We present a rotated hyperbolic wrapped normal distribution (RoWN), a simple yet effective alteration of a hyperbolic wrapped normal distribution (HWN).
no code implementations • 4 May 2022 • Zhenyue Qin, Yang Liu, Madhawa Perera, Tom Gedeon, Pan Ji, Dongwoo Kim, Saeed Anwar
To this end, we present a review in the form of a taxonomy on existing works of skeleton-based action recognition.
1 code implementation • 30 Nov 2021 • Saemi Moon, Myeonghyeon Kim, Zhenyue Qin, Yang Liu, Dongwoo Kim
Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the privacy of subjects while having competitive recognition performance.
1 code implementation • 1 Nov 2021 • Hoyoung Kim, Seunghyuk Cho, Dongwoo Kim, Jungseul Ok
Crowdsourcing systems enable us to collect large-scale dataset, but inherently suffer from noisy labels of low-paid workers.
no code implementations • 14 Sep 2021 • Dongwoo Kim, Young Jun Lee
Conditional on first-dose coverage, an increased fraction with two doses appears to offer no further reductions in new cases and deaths.
no code implementations • 19 Jun 2021 • Zhenyue Qin, Dongwoo Kim, Tom Gedeon
We develop an informative class activation map (infoCAM).
no code implementations • 19 Jun 2021 • Zhenyue Qin, Dongwoo Kim, Tom Gedeon
We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators.
1 code implementation • 24 May 2021 • Zhenyue Qin, Saeed Anwar, Dongwoo Kim, Yang Liu, Pan Ji, Tom Gedeon
Such GNNs are incapable of learning relative positions between graph nodes within a graph.
1 code implementation • 4 May 2021 • Zhenyue Qin, Yang Liu, Pan Ji, Dongwoo Kim, Lei Wang, Bob McKay, Saeed Anwar, Tom Gedeon
Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.
Ranked #20 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • CVPR 2021 • Yang Liu, Zhenyue Qin, Saeed Anwar, Pan Ji, Dongwoo Kim, Sabrina Caldwell, Tom Gedeon
InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise.
no code implementations • 26 Mar 2021 • Sean Li, Dongwoo Kim, Qing Wang
The proposed model is shown to generalize well to both homophilic and heterophilic graphs.
1 code implementation • 2 Mar 2021 • Jonghyuk Park, Sukhyun Cho, Dongwoo Kim, Oleksandr Bailo, Heewoong Park, Sanghoon Hong, Jonghun Park
Furthermore, in order to compute the motion similarity from these datasets, we propose a deep learning model that produces motion embeddings suitable for measuring the similarity between different motions of each human body part.
no code implementations • 1 Jan 2021 • Shouheng Li, Dongwoo Kim, Qing Wang
The proposed model has been shown to generalize well to both assortative and disassortative graphs.
2 code implementations • LREC 2020 • Yo Joong Choe, Kyubyong Park, Dongwoo Kim
We wrap our dataset and model in an easy-to-use Python library, which supports downloading and retrieving top-k word translations in any of the supported language pairs as well as computing top-k word translations for custom parallel corpora.
1 code implementation • 25 Nov 2019 • Zhenyue Qin, Dongwoo Kim, Tom Gedeon
We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption.
no code implementations • 7 Oct 2019 • Zhenyue Qin, Dongwoo Kim
Under this view, we can naturally and mathematically derive log-softmax as an inherent component in a neural network for evaluating the conditional mutual information between network output vectors and labels given an input datum.
no code implementations • ICML 2018 • Dongwoo Kim, Christian Walder
Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction.
no code implementations • ICML 2018 • Christian J. Walder, Dongwoo Kim
We present a neural sequence model designed specifically for symbolic music.
no code implementations • TACL 2017 • Jooyeon Kim, Dongwoo Kim, Alice Oh
Second, it models each author's influence on citations of a paper based on the topics of the cited papers, as well as the citing papers.
no code implementations • 1 Dec 2016 • Christian Walder, Dongwoo Kim
For the case of highly permissive constraint sets, we find that sampling is to be preferred due to the overly regular nature of the optimisation based results.
no code implementations • 21 Aug 2016 • Dongwoo Kim, Lexing Xie, Cheng Soon Ong
Knowledge graph construction consists of two tasks: extracting information from external resources (knowledge population) and inferring missing information through a statistical analysis on the extracted information (knowledge completion).
no code implementations • 12 Mar 2015 • Nebojsa Jojic, Alessandro Perina, Dongwoo Kim
The counting grid is a grid of microtopics, sparse word/feature distributions.
no code implementations • 22 Mar 2014 • Dongwoo Kim, Alice Oh
We present the \textit{hierarchical Dirichlet scaling process} (HDSP), a Bayesian nonparametric mixed membership model.