Lists (5)
Stars
About Code release for "Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy" (ICLR 2022 Spotlight), https://openreview.net/forum?id=LzQQ89U1qm_
Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).
Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)
Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency
A Model for Natural Language Attack on Text Classification and Inference
Robust Attribution Regularization
Code for the paper "Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation"
A game theoretic approach to explain the output of any machine learning model.
Interpretability and explainability of data and machine learning models
XAI-Bench is a library for benchmarking feature attribution explainability techniques
Repository for paper ``IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution‘’
Tensorflow 2.1 implementation of LRP for LSTMs
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah
Large Language Models Are Reasoning Teachers (ACL 2023)
Log anomaly detection based on MogrifierLSTM + CNN
Multi-Task Deep Neural Networks for Natural Language Understanding
Adversarial Training for Natural Language Understanding
试图复现paper:Improved Text Classification via Contrastive Adversarial Training
基于 Tensorflow，仿 Scikit-Learn 设计的深度学习自然语言处理框架。支持 40 余种模型类，涵盖语言模型、文本分类、NER、MRC、知识蒸馏等各个领域
GAIA, with the full name Generic AIOps Atlas, is an overall dataset for analyzing operation problems such as anomaly detection, log analysis, fault localization, etc.
Model interpretability and understanding for PyTorch
Open-Sora: Democratizing Efficient Video Production for All
Transformer based on a variant of attention that is linear complexity in respect to sequence length
A high performance implementation of HDBSCAN clustering.
Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction