I am an applied scientist (2020/08 - Present) at Amazon Search. I received my Ph.D. from the School of Computer Science at CMU under supervision of Prof. Yiming Yang. Prior to CMU, I got my B.S. from National Taiwan University under supervision of Prof. Chih-Jen Lin.

I have interned at Google Research (2019), working with Felix Yu and Sanjiv Kumar. I have also interned at Amazon Search (2018), working with Hsiang-Fu Yu and Inderjit Dhillon.

I am interested in scalable machine learning algorithms for large output space problems. My research covers extreme multi-label classification, large-scale retrieval, and approximated nearest neighbor search.

Publications

PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models
Wei-Cheng Chang, Jyun-Yu Jiang, Jiong Zhang, Mutasem Al-Darabsah, Choon Hui Teo, Cho-Jui Hsieh, Hsiang-Fu Yu, S. V. N. Vishwanathan
To appear in WSDM 2024. [pdf] [code]

Build faster with less: A journey to accelerate sparse model building for semantic matching in product search
Jiong Zhang, Yau-Shian Wang, Wei-Cheng Chang, Wei Li, Jyun-Yu Jiang, Cho-Jui Hsieh, Hsiang-Fu Yu
CIKM 2023. [pdf]

PINA: Leveraging Side Information in eXtreme Multilabel Classification via Predicted Instance Neighborhood Aggregation
Eli Chien, Jiong Zhang, Jyun-Yu Jiang, Wei-Cheng Chang, Cho-Jui Hsieh, Olgica Milenkovic and Hsiang-Fu Yu
ICML 2023. [pdf] [code]

Uncertainty in Extreme Multi-label Classification
Jyun-Yu Jiang, Wei-Cheng Chang, Jiong Zhang, Cho-Jui Hsieh and Hsiang-Fu Yu
SIGIR 2023. [pdf]

FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search
Patrick H. Chen, Wei-Cheng Chang, Jyun-Yu Jiang, Hsiang-Fu Yu, Inderjit S. Dhillon and Cho-Jui Hsieh
The Web Conference (WWW) 2023. [pdf] [code]

Extreme Zero-Shot Learning for Extreme Text Classification
Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu and Inderjit Dhillon
NAACL 2022. [pdf] [code]

Relevance under the Iceberg: Reasonable Prediction for Extreme Multi-label Classification
Jyun-Yu Jiang, Wei-Cheng Chang, Jiong Zhang, Cho-Jui Hsieh, Hsiang-Fu Yu
SIGIR 2022. [pdf]

PECOS: Prediction for Enormous and Correlated Output Spaces
Hsiang-Fu Yu, Kai Zhong, Jiong Zhang, Wei-Cheng Chang, and Inderjit Dhillon
JMLR 2022. [pdf] [code] [blog]

Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
Eli Chien, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Jiong Zhang, Olgica Milenkovic and Inderjit Dhillon
ICLR 2022. [arxiv] [code] (1st place on three OGB leaderboards as of 2021/11/08)

Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification
Jiong Zhang, Wei-Cheng Chang, Hsiang-Fu Yu and Inderjit Dhillon
NeurIPS 2021. [arxiv] [code] [blog]

Label Disentanglement in Partition-based Extreme Multilabel Classification
Xuanqing Liu, Wei-Cheng Chang, Hsiang-Fu Yu, Cho-Jui Hsieh, and Inderjit Dhillon
NeurIPS 2021. [arxiv] [code] [blog]

Extreme Multi-Label Learning For Semantic Matching In Product Search
Wei-Cheng Chang, Daniel Jiang, Hsiang-Fu Yu, Choon Hui Teo, Jiong Zhang, Kai Zhong, Kedarnath Kolluri, Qie Hu, Nikhil Shandilya, Vyacheslav Ievgrafov, Japinder Singh, Inderjit Dhillon
KDD 2021. [arxiv] [blog]

Taming pretrained transformers for extreme multi-label text classification
Wei-Cheng Chang, Hsiang-Fu Yu, Kai Zhong, Yiming Yang and Inderjit Dhillon
KDD 2020. [arxiv] [code]

Pre-training Tasks for Embedding-based Large-scale Retrieval
Wei-Cheng Chang, Felix X. Yu, Yin-Wen Chang, Yiming Yang, Sanjiv Kumar
ICLR 2020. [arxiv]

Implicit Kernel Learning
Chun-Liang Li, Wei-Cheng Chang, Youssef Mroueh, Yiming Yang, Barnabás Póczos
AISTATS 2019. [arxiv]

Kernel Change-point Detection with Auxiliary Deep Generative Models
Wei-Cheng Chang, Chun-Liang Li, Yiming Yang, Barnabás Póczos
ICLR 2019. [arxiv] [code]

Modeling Long-and Short-Term Temporal Patterns with Deep Neural Networks
Guokun Lai, Wei-Cheng Chang, Yiming Yang, Hanxiao Liu
SIGIR 2018. [arxiv] [code]

MMD GAN: Towards Deeper Understanding of Moment Matching Network
Chun-Liang Li* , Wei-Cheng Chang* , Yu Cheng, Yiming Yang, Barnabás Póczos
NeurIPS 2017. [arxiv] [code]

Data-driven Random Fourier Features using Stein Effect
Wei-Cheng Chang, Chun-Liang Li, Yiming Yang, Barnabás Póczos
IJCAI 2017. [arxiv] (best student paper runner up)

Deep Learning for Extreme Multi-label Text Classification
Jingzhou Liu, Wei-Cheng Chang, Yuexin Wu, Yiming Yang
SIGIR 2017. [pdf] [code]

Cross-domain Kernel Induction for Transfer Learning
Wei-Cheng Chang* , Yuexin Wu* , Hanxiao Liu, Yiming Yang
AAAI 2017. [pdf] [code]