no code implementations • 7 Apr 2024 • Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, Jiayi Huang
Expert parallelism has been introduced as a strategy to distribute the computational workload of sparsely-gated mixture-of-experts (MoE) models across multiple computing devices, facilitating the execution of these increasingly large-scale models.
1 code implementation • 17 Mar 2024 • Peilin Zhou, You-Liang Huang, Yueqi Xie, Jingqi Gao, Shoujin Wang, Jae Boum Kim, Sunghun Kim
Intriguingly, the conclusion drawn from our study is that, certain data augmentation strategies can achieve similar or even superior performance compared with some CL-based methods, demonstrating the potential to significantly alleviate the data sparsity issue with fewer computational overhead.
no code implementations • 26 Feb 2024 • Peiyan Zhang, Chaozhuo Li, Liying Kang, Feiran Huang, Senzhang Wang, Xing Xie, Sunghun Kim
Moreover, we show that existing contrastive objective learns the low-frequency component of the augmentation graph and propose a high-frequency component (HFC)-aware contrastive learning objective that makes the learned embeddings more distinctive.
2 code implementations • 23 Dec 2023 • Dahyun Kim, Chanjun Park, Sanghoon Kim, Wonsung Lee, Wonho Song, Yunsu Kim, Hyeonwoo Kim, Yungi Kim, Hyeonju Lee, Jihoo Kim, Changbae Ahn, Seonghoon Yang, Sukyung Lee, Hyunbyung Park, Gyoungjin Gim, Mikyoung Cha, Hwalsuk Lee, Sunghun Kim
We introduce SOLAR 10. 7B, a large language model (LLM) with 10. 7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks.
no code implementations • 28 Aug 2023 • Peiyan Zhang, Yuchen Yan, Chaozhuo Li, Senzhang Wang, Xing Xie, Sunghun Kim
Graph Neural Networks (GNNs) have emerged as promising solutions for collaborative filtering (CF) through the modeling of user-item interaction graphs.
no code implementations • 21 Aug 2023 • Peiyan Zhang, Haoyang Liu, Chaozhuo Li, Xing Xie, Sunghun Kim, Haohan Wang
Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion.
1 code implementation • 18 Aug 2023 • Peilin Zhou, Qichen Ye, Yueqi Xie, Jingqi Gao, Shoujin Wang, Jae Boum Kim, Chenyu You, Sunghun Kim
Our empirical analysis of some representative Transformer-based SR models reveals that it is not uncommon for large attention weights to be assigned to less relevant items, which can result in inaccurate recommendations.
1 code implementation • 23 May 2023 • Peiyan Zhang, Yuchen Yan, Chaozhuo Li, Senzhang Wang, Xing Xie, Guojie Song, Sunghun Kim
Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is overwritten by updates for new graphs.
no code implementations • 6 Mar 2023 • Peiyan Zhang, Sunghun Kim
In this article, we offer a systematic survey of incremental update for neural recommender systems.
1 code implementation • 28 Feb 2023 • Yueqi Xie, Jingqi Gao, Peilin Zhou, Qichen Ye, Yining Hua, Jaeboum Kim, Fangzhao Wu, Sunghun Kim
To address these issues, we propose the REMI framework, consisting of an Interest-aware Hard Negative mining strategy (IHN) and a Routing Regularization (RR) method.
2 code implementations • CVPR 2023 • Renjie Pi, Weizhong Zhang, Yueqi Xie, Jiahui Gao, Xiaoyu Wang, Sunghun Kim, Qifeng Chen
Specifically, we first reserve a short trajectory of global model snapshots on the server.
no code implementations • 10 Nov 2022 • Yueqi Xie, Weizhong Zhang, Renjie Pi, Fangzhao Wu, Qifeng Chen, Xing Xie, Sunghun Kim
Since at each round, the number of tunable parameters optimized on the server side equals the number of participating clients (thus independent of the model size), we are able to train a global model with massive parameters using only a small amount of proxy data (e. g., around one hundred samples).
1 code implementation • 10 Nov 2022 • Peilin Zhou, Jingqi Gao, Yueqi Xie, Qichen Ye, Yining Hua, Jae Boum Kim, Shoujin Wang, Sunghun Kim
Therefore, we propose Equivariant Contrastive Learning for Sequential Recommendation (ECL-SR), which endows SR models with great discriminative power, making the learned user behavior representations sensitive to invasive augmentations (e. g., item substitution) and insensitive to mild augmentations (e. g., featurelevel dropout masking).
2 code implementations • 5 Aug 2022 • Juyong Jiang, Binqing Wu, Ling Chen, Kai Zhang, Sunghun Kim
On the one hand, our model simultaneously incorporates spatial (node-wise) embeddings and temporal (time-wise) embeddings to account for heterogeneous space-and-time convolutions; on the other hand, it uses GAN structure to systematically evaluate statistical consistencies between the real and the predicted time series in terms of both the temporal trending and the complex spatial-temporal dependencies.
1 code implementation • 26 Jun 2022 • Peiyan Zhang, Jiayan Guo, Chaozhuo Li, Yueqi Xie, Jaeboum Kim, Yan Zhang, Xing Xie, Haohan Wang, Sunghun Kim
Based on this observation, we intuitively propose to remove the GNN propagation part, while the readout module will take on more responsibility in the model reasoning process.
1 code implementation • 26 Jun 2022 • Jiayan Guo, Peiyan Zhang, Chaozhuo Li, Xing Xie, Yan Zhang, Sunghun Kim
Session-based recommendation (SBR) aims to predict the user next action based on the ongoing sessions.
1 code implementation • 18 May 2022 • Juyong Jiang, Peiyan Zhang, Yingtao Luo, Chaozhuo Li, Jae Boum Kim, Kai Zhang, Senzhang Wang, Xing Xie, Sunghun Kim
Sequential recommendation (SR) aims to model users dynamic preferences from a series of interactions.
1 code implementation • 23 Apr 2022 • Yueqi Xie, Peilin Zhou, Sunghun Kim
Motivated by this, we propose Decoupled Side Information Fusion for Sequential Recommendation (DIF-SR), which moves the side information from the input to the attention layer and decouples the attention calculation of various side information and item representation.
1 code implementation • 13 Dec 2021 • Juyong Jiang, Peiyan Zhang, Yingtao Luo, Chaozhuo Li, Jaeboum Kim, Kai Zhang, Senzhang Wang, Sunghun Kim
Our approach leverages bidirectional temporal augmentation and knowledge-enhanced fine-tuning to synthesize authentic pseudo-prior items that \emph{retain user preferences and capture deeper item semantic correlations}, thus boosting the model's expressive power.
1 code implementation • 20 Apr 2020 • Jung-Woo Ha, Kihyun Nam, Jingu Kang, Sang-Woo Lee, Sohee Yang, Hyunhoon Jung, Eunmi Kim, Hyeji Kim, Soojin Kim, Hyun Ah Kim, Kyoungtae Doh, Chan Kyu Lee, Nako Sung, Sunghun Kim
Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • IJCNLP 2019 • Fuxiang Chen, Seung-won Hwang, Jaegul Choo, Jung-Woo Ha, Sunghun Kim
Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL.
3 code implementations • ICLR 2019 • Xiaodong Gu, Kyunghyun Cho, Jung-Woo Ha, Sunghun Kim
Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling.
no code implementations • 16 Dec 2017 • Jung-Woo Ha, Adrian Kim, Chanju Kim, Jang-Yeon Park, Sunghun Kim
Music highlights are valuable contents for music services.
no code implementations • 16 Dec 2017 • Nako Sung, Minkyu Kim, Hyunwoo Jo, Youngil Yang, Jingwoong Kim, Leonard Lausen, Youngkwan Kim, Gayoung Lee, Dong-Hyun Kwak, Jung-Woo Ha, Sunghun Kim
However, researchers are still required to perform a non-trivial amount of manual tasks such as GPU allocation, training status tracking, and comparison of models with different hyperparameter settings.
34 code implementations • CVPR 2018 • Yunjey Choi, Min-Je Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, Jaegul Choo
To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model.
Ranked #1 on Image-to-Image Translation on RaFD (using extra training data)
no code implementations • 25 Apr 2017 • Xiaodong Gu, Hongyu Zhang, Dongmei Zhang, Sunghun Kim
They rely on the sparse availability of bilingual projects, thus producing a limited number of API mappings.
no code implementations • 27 May 2016 • Xiaodong Gu, Hongyu Zhang, Dongmei Zhang, Sunghun Kim
We propose DeepAPI, a deep learning based approach to generate API usage sequences for a given natural language query.