Layer 6 Labs

dgm-eval

Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

DropoutNet

Code for the NeurIPS'17 paper "DropoutNet: Addressing Cold Start in Recommender Systems"

fusemix

Data-Efficient Multimodal Fusion on a Single GPU

GSS

Code for the NeurIPS'19 paper "Guided Similarity Separation for Image Retrieval"

HGCF

Code for the WWW'21 paper "HGCF: Hyperbolic Graph Convolution Networks for Collaborative Filtering"

ProxyFL

Code accompanying the paper "Decentralized Federated Learning through Proxy Model Sharing"

RecSys2018

1'st Place Approach by Layer6 AI to the 2018 ACM RecSys Challenge

SGG-Seq2Seq

Code for the ICCV'21 paper "Context-aware Scene Graph Generation with Seq2Seq Transformers"

T-Fixup

Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"

xpool

https://layer6ai-labs.github.io/xpool/

layer6ai-labs/DropoutNet

Code for the NeurIPS'17 paper "DropoutNet: Addressing Cold Start in Recommender Systems"

layer6ai-labs/dgm-eval

Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

layer6ai-labs/xpool

https://layer6ai-labs.github.io/xpool/

layer6ai-labs/RecSys2018

1'st Place Approach by Layer6 AI to the 2018 ACM RecSys Challenge

layer6ai-labs/ProxyFL

Code accompanying the paper "Decentralized Federated Learning through Proxy Model Sharing"

layer6ai-labs/fusemix

Data-Efficient Multimodal Fusion on a Single GPU

layer6ai-labs/DuETT

Code for "DuETT: Dual Event Time Transformer for Electronic Health Records"

layer6ai-labs/WinIT

Code for the ICLR'23 paper "Temporal Dependencies in Feature Importance for Time Series Prediction"

layer6ai-labs/tr0n

layer6ai-labs/calo-forest

A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.

layer6ai-labs/fair-dp

Code accompanying the paper "Disparate Impact in Differential Privacy from Gradient Misalignment".

layer6ai-labs/lfr

Code for the ICLR'24 paper "Self-supervised Representation Learning From Random Data Projectors

layer6ai-labs/two_step_zoo

Codebase accompanying the paper "Diagnosing and Fixing Manifold Overfitting in Deep Generative Models"

layer6ai-labs/UoMH

layer6ai-labs/BNPO

layer6ai-labs/hitl-conformal-prediction

Human in the Loop Conformal Prediction

layer6ai-labs/ssl-robustness

Codebase for benchmarking robustness of Self-Supervised Learning across diverse downstream tasks

layer6ai-labs/implicit-manifolds

layer6ai-labs/Tabular-Class-Conditioned-SSL

layer6ai-labs/dgm_manifold_survey

layer6ai-labs/dgm_ood_detection

Code for the paper "A Geometric Explanation of the Likelihood OOD Detection Paradox"

layer6ai-labs/hgnn-dr

layer6ai-labs/dgm_geometry

layer6ai-labs/dp-cert

A framework for providing certified robustness guarantees with differentially private models

layer6ai-labs/DropoutNet-Data

data for DropoutNet

layer6ai-labs/DiMS

Code for the ACL'23 paper "DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation"

layer6ai-labs/HiBench

HiBench is a big data benchmark suite.

layer6ai-labs/tpcds-spark

layer6ai-labs/tpch-spark

TPC-H queries in Apache Spark SQL using native DataFrames API

layer6ai-labs/tuneful-code