Skip to content
@mala-lab

Machine Learning & Applications (MaLA)

A research team working with Guansong Pang, specializing in handling unknown or abnormal data instances

Introduction

SMU Machine Learning & Applications (MaLA) Lab consists of a team led by Assistant Professor Guansong Pang in the School of Computing and Information Systems at Singapore Management University (SMU), working on a variety of machine learning, data mining, and computer vision problems.

We have a focal research theme on recognizing and generalizing to abnormal, unknown, or unseen data for building trustworthy AI systems in open worlds. Some research areas of particular interest include:

   🍿 Anomaly detection

   🍿 Open-world learning (out-of-distribution detection, open-set recognition, long-tailed classification, continual learning, open-vocabulary learning, etc.)

   🍿 Deep learning and foundation models on graphs, time series, tabular data

   🍿 Security and safety in foundation models (hallucination mitigation, AI-generated content detection, defense against model/data attacks, etc.)

The team also explores some pivotal real-world applications of these areas, such as network intrusion detection, fraud detection, early detection of diseases/faults, learning from biomedicine data, industrial defect detection, biometric anti-spoofing, hate speech detection, etc.

The team has been actively collaborating with research teams led by various researchers, e.g., Prof. Ling Chen, Prof. Christopher Leckie, Prof. Xiao Bai, Prof. Peng Wang, Prof. Chunhua Shen, Prof. Ming-Sheng Shang, Prof. Kai-Ming Ting, and Prof. Gustavo Carneiro.

Pinned Loading

  1. InCTRL InCTRL Public

    Official implementation of CVPR'24 paper 'Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts'.

    Python 176 21

  2. Awesome-Deep-Graph-Anomaly-Detection Awesome-Deep-Graph-Anomaly-Detection Public

    Official repository for survey paper "Deep Graph Anomaly Detection: A Survey and New Perspectives", including diverse types of resources for graph anomaly detection.

    100 9

  3. NegPrompt NegPrompt Public

    The official implementation of CVPR 24' Paper "Learning Transferable Negative Prompts for Out-of-Distribution Detection"

    Python 55 6

  4. SIC-CADS SIC-CADS Public

    Code Implementation of "Simple Image-level Classification Improves Open-vocabulary Object Detection" (AAAI'24)

    Python 25 4

  5. GGAD GGAD Public

    Official implementation for NeurIPS'24 paper "Generative Semi-supervised Graph Anomaly Detection"

    Python 51 2

  6. TPP TPP Public

    Official code for "Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach" (NeurIPS 2024).

    Python 11 2

Repositories

Showing 10 of 52 repositories

Most used topics

Loading…