CS 732 - Spring 2025 - Advanced Machine Learning

News:

Class schedule: Weddays 11:30 - 2:20 pm, KUPF 209
Instructor: Zhi Wei ; Email: zhiwei@njit.edu; Office: GITC 4214-C
Office hours (GITC 4214-C): Wed 2:30 pm - 4:30 pm, Thur 2:00-3:00pm, or by appointment.

Syllabus

Textbook: The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Second Edition)

Presentation schedule, Please download slides from Canvas.

Tentative Date Lecture Topic Presentation Leaders Paper presentation Readings
1/22 Introduction

PCA

Ch 14.5
Jolliffe and Cadima, Principal component analysis: a review and recent developments
Tipping and Bishop, Probabilistic principal component analysis
1/29   1. Oduru Ramesh, Mohith Reddy
2. Naidan Zhang
  1. Shang and Zhou. Spatially aware dimension reduction for spatial transcriptomics. Nature Communications 2022.
  2. Liu et al. Joint dimension reduction and clustering analysis of single-cell RNA-seq and spatial transcriptomics data. Nucleic Acids Research, 2022.
Gu and Shen, Generalized probabilistic principal component analysis of correlated data, Journal of Machine Learning Research 2020.
2/5  

1. He, Zirui

2. Dang, Huu Phuoc
  1. Yang et al, GraphPCA: a fast and interpretable dimension reduction algorithm for spatial transcriptomics data, Genome Biology 2024.
  2. Abid et al, Exploring patterns enriched in a dataset with contrastive principal component analysis, Nature Communications 2018.
2/12 NMF

1. Vaibhav Bora

2. Xuan Zhang 
  1. Townes and Engelhardt Nonnegative spatial factorization applied to spatial genomics. Nature Methods 2023.
  2. Elosua-Bayes et al. SPOTlight: seeded NMF regression to deconvolute spatial transcriptomics spots with single-cell transcriptomes. Nucleic Acids Research, 2021.
Quick Introduction to Nonnegative Matrix Factorization
2/19  

1. Balakrishnan, Hariharasudhan

2. Bandharu, Sutikshan
  1. Duren et al. Integrative analysis of single-cell genomics data by coupled nonnegative matrix factorizations. Proceedings of the National Academy of Sciences, 2018.
  2. Kriebel and Welch, UINMF performs mosaic integration of single-cell multi-omic datasets using nonnegative matrix factorization, Nature Communications 2022.
 
2/26 Autoencoder

1. Luan, Feiyang

2. Ghosh, Subhodeep
  1. Tian et al, Clustering single-cell RNA-seq data with a model-based deep learning approach, Nature Machine Intelligence 2019  1:191-198.
  2. Chen et al. Deep soft K-means clustering with self-training for single-cell RNA sequence data. NAR Genomics and Bioinformatics, 2020.

Tschannen and Lucic, Recent advances in autoencoder-based representation learning, arXiv 2018.
Xie et al, Unsupervised Deep Embedding for Clustering Analysis , ICML 2016.
Guo et al, Improved Deep Embedded Clustering with Local Structure Preservation , IJCAI 2017.
3/5  

1. Nakarmi, Avina

2. Patil, Sarang
  1. Tian et al, Model-based deep embedding for constrained clustering analysis of single cell RNA-seq data , Nature Communications, 2021.
  2. Lin et al, Clustering of single-cell multi-omics data with a multimodal deep learning method, Nature Communications, 2022.
 
3/12  

1. Ãœnal, Altay

2. ALBarqawi, Ahmad
  1. Piran et al, Disentanglement of single-cell data with biolord, Nature Biotechnology, 2024.
  2. Moinfar and Theis. Unsupervised Deep Disentangled Representation of Single-Cell Omics. bioRxiv, 2024.
Gabbay et al, An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild , NeurIPS 2021.
3/19 Spring Break      
3/26 Take Home Midterm-Exam/Project  
4/2 Presentation of Midterm Project  
 
4/9 VAE

1. Jianyi Yang

2. Sarang Patil

  1. Lopez et al, Deep generative modeling for single-cell transcriptomics, Nature Methods, 2018.
  2. Tian et al, Dependency-aware deep generative models for multitasking analysis of spatial omics data, Nature Methods, 2024.
 C Doersch, Tutorial on variational autoencoders
Blei et al, Variational inference: A review for statisticians
4/16  

1. Suhodeep Ghosh

2. Avina Nakarmi
  1. Weinberger et al, Isolating salient variations of interest in single-cell data with contrastiveVI, Nature Methodsn, 2023.
  2. Shu et al, Modeling gene regulatory networks using neural network architectures, Nature Computational Science, 2021.
 Yu et al, DAG-GNN: DAG Structure Learning with Graph Neural Networks, ICML, 2019
4/23 Transformer

1. Oduru Ramesh, Mohith

2. Zirui He
  1. Yang et al, scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data , Nature Machine Intelligence, 2022.
  2. Theodoris et al, Transfer learning enables predictions in network biology, Nature, 2023.
 Vaswani et al, Attention is all you need, NIPS, 2017
Khan et al, Reusability report: Learning the transcriptional grammar in single-cell RNA-sequencing data using transformers, Nature Machine Intelligence, 2023
Boiarsky et al, Deeper evaluation of a single-cell foundation model, Nature Machine Intelligence, 2024
4/30  

1. Altay Unal

2. Ahmad Albarqawi
  1. Cui et al, scGPT: toward building a foundation model for single-cell multi-omics using generative AI , Nature Methods, 2024.
  2. Hao et al, Large-scale foundation model on single-cell transcriptomics, Nature Methods, 2024.
  
5/7 Friday Schedule      

Academic integrityy

Modifications to syllabus