Implementation of the paper "Shapley Explanation Networks"

Overview

Shapley Explanation Networks

Implementation of the paper "Shapley Explanation Networks" at ICLR 2021. Note that this repo heavily uses the experimental feature of named tensors in PyTorch. As it was really confusing to implement the ideas for the authors, we find it tremendously easier to use this feature.

Dependencies

For running only ShapNets, one would mostly only need PyTorch, NumPy, and SciPy.

Usage

For a Shapley Module:

import torch
import torch.nn as nn
from ShapNet.utils import ModuleDimensions
from ShapNet import ShapleyModule

b_size = 3
features = 4
out = 1
dims = ModuleDimensions(
    features=features,
    in_channel=1,
    out_channel=out
)

sm = ShapleyModule(
    inner_function=nn.Linear(features, out),
    dimensions=dims
)
sm(torch.randn(b_size, features), explain=True)

For a Shallow ShapNet

import torch
import torch.nn as nn
from ShapNet.utils import ModuleDimensions
from ShapNet import ShapleyModule, OverlappingShallowShapleyNetwork

batch_size = 32
class_num = 10
dim = 32

overlapping_modules = [
    ShapleyModule(
        inner_function=nn.Sequential(nn.Linear(2, class_num)),
        dimensions=ModuleDimensions(
            features=2, in_channel=1, out_channel=class_num
        ),
    ) for _ in range(dim * (dim - 1) // 2)
]
shallow_shapnet = OverlappingShallowShapleyNetwork(
    list_modules=overlapping_modules
)
inputs = torch.randn(batch_size, dim, ), )
shallow_shapnet(torch.randn(batch_size, dim, ), )
output, bias = shallow_shapnet(inputs, explain=True, )

For a Deep ShapNet

import torch
import torch.nn as nn
from ShapNet.utils import ModuleDimensions
from ShapNet import ShapleyModule, ShallowShapleyNetwork, DeepShapleyNetwork

dim = 32
dim_input_channels = 1
class_num = 10
inputs = torch.randn(32, dim, ), )


dims = ModuleDimensions(
    features=dim,
    in_channel=dim_input_channels,
    out_channel=class_num
)
deep_shapnet = DeepShapleyNetwork(
    list_shapnets=[
        ShallowShapleyNetwork(
            module_dict=nn.ModuleDict({
                "(0, 2)": ShapleyModule(
                    inner_function=nn.Linear(2, class_num),
                    dimensions=ModuleDimensions(
                        features=2, in_channel=1, out_channel=class_num
                    )
                )},
            ),
            dimensions=ModuleDimensions(dim, 1, class_num)
        ),
    ],
)
deep_shapnet(inputs)
outputs = deep_shapnet(inputs, explain=True, )

For a vision model:

import numpy as np
import torch
import torch.nn as nn

# =============================================================================
# Imports {\sc ShapNet}
# =============================================================================
from ShapNet import DeepConvShapNet, ShallowConvShapleyNetwork, ShapleyModule
from ShapNet.utils import ModuleDimensions, NAME_HEIGHT, NAME_WIDTH, \
    process_list_sizes

num_channels = 3
num_classes = 10
height = 32
width = 32
list_channels = [3, 16, 10]
pruning = [0.2, 0.]
kernel_sizes = process_list_sizes([2, (1, 3), ])
dilations = process_list_sizes([1, 2])
paddings = process_list_sizes([0, 0])
strides = process_list_sizes([1, 1])

args = {
    "list_shapnets": [
        ShallowConvShapleyNetwork(
            shapley_module=ShapleyModule(
                inner_function=nn.Sequential(
                    nn.Linear(
                        np.prod(kernel_sizes[i]) * list_channels[i],
                        list_channels[i + 1]),
                    nn.LeakyReLU()
                ),
                dimensions=ModuleDimensions(
                    features=int(np.prod(kernel_sizes[i])),
                    in_channel=list_channels[i],
                    out_channel=list_channels[i + 1])
            ),
            reference_values=None,
            kernel_size=kernel_sizes[i],
            dilation=dilations[i],
            padding=paddings[i],
            stride=strides[i]
        ) for i in range(len(list_channels) - 1)
    ],
    "reference_values": None,
    "residual": False,
    "named_output": False,
    "pruning": pruning
}

dcs = DeepConvShapNet(**args)

Citation

If this is useful, you could cite our work as

@inproceedings{
wang2021shapley,
title={Shapley Explanation Networks},
author={Rui Wang and Xiaoqian Wang and David I. Inouye},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=vsU0efpivw}
}
Owner
Prof. David I. Inouye's research lab at Purdue University.
Transformer part of 12th place solution in Riiid! Answer Correctness Prediction

kaggle_riiid Transformer part of 12th place solution in Riiid! Answer Correctness Prediction. Please see here for more information. Execution You need

Sakami Kosuke 2 Apr 23, 2022
Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics.

Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics. By Andres Milioto @ University of Bonn. (for the new P

Photogrammetry & Robotics Bonn 314 Dec 30, 2022
[ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation

RTD-Net (ICCV 2021) This repo holds the codes of paper: "Relaxed Transformer Decoders for Direct Action Proposal Generation", accepted in ICCV 2021. N

Multimedia Computing Group, Nanjing University 80 Nov 30, 2022
RLBot Python bindings for the Rust crate rl_ball_sym

RLBot Python bindings for rl_ball_sym 0.6 Prerequisites: Rust & Cargo Build Tools for Visual Studio RLBot - Verify that the file %localappdata%\RLBotG

Eric Veilleux 2 Nov 25, 2022
Flexible Networks for Learning Physical Dynamics of Deformable Objects (2021)

Flexible Networks for Learning Physical Dynamics of Deformable Objects (2021) By Jinhyung Park, Dohae Lee, In-Kwon Lee from Yonsei University (Seoul,

Jinhyung Park 0 Jan 09, 2022
Leveraging Two Types of Global Graph for Sequential Fashion Recommendation, ICMR 2021

This is the repo for the paper: Leveraging Two Types of Global Graph for Sequential Fashion Recommendation Requirements OS: Ubuntu 16.04 or higher ver

Yujuan Ding 10 Oct 10, 2022
Trajectory Variational Autoencder baseline for Multi-Agent Behavior challenge 2022

MABe_2022_TVAE: a Trajectory Variational Autoencoder baseline for the 2022 Multi-Agent Behavior challenge This repository contains jupyter notebooks t

Andrew Ulmer 15 Nov 08, 2022
Analyzing basic network responses to novel classes

novelty-detection Analyzing how AlexNet responds to novel classes with varying degrees of similarity to pretrained classes from ImageNet. If you find

Noam Eshed 34 Oct 02, 2022
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

Ranger-Deep-Learning-Optimizer Ranger - a synergistic optimizer combining RAdam (Rectified Adam) and LookAhead, and now GC (gradient centralization) i

Less Wright 1.1k Dec 21, 2022
Code release for SLIP Self-supervision meets Language-Image Pre-training

SLIP: Self-supervision meets Language-Image Pre-training What you can find in this repo: Pre-trained models (with ViT-Small, Base, Large) and code to

Meta Research 621 Dec 31, 2022
Reimplement of SimSwap training code

SimSwap-train Reimplement of SimSwap training code Instructions 1.Environment Preparation (1)Refer to the README document of SIMSWAP to configure the

seeprettyface.com 111 Dec 31, 2022
COPA-SSE contains crowdsourced explanations for the Balanced COPA dataset

COPA-SSE Repository for COPA-SSE: Semi-Structured Explanations for Commonsense Reasoning. COPA-SSE contains crowdsourced explanations for the Balanced

Ana Brassard 5 Jul 31, 2022
EasyMocap is an open-source toolbox for markerless human motion capture from RGB videos.

EasyMocap is an open-source toolbox for markerless human motion capture from RGB videos. In this project, we provide the basic code for fitt

ZJU3DV 2.2k Jan 05, 2023
Rl-quickstart - Reinforcement Learning Quickstart

Reinforcement Learning Quickstart To get setup with the repository, git clone ht

UCLA DataRes 3 Jun 16, 2022
PyTea: PyTorch Tensor shape error analyzer

PyTea: PyTorch Tensor Shape Error Analyzer paper project page Requirements node.js = 12.x python = 3.8 z3-solver = 4.8 How to install and use # ins

ROPAS Lab. 240 Jan 02, 2023
Space Ship Simulator using python

FlyOver Basic space-ship simulator using python How to run? Just double click run.py What modules do i need? All modules that i currently using is bui

0 Oct 09, 2022
Efficient semidefinite bounds for multi-label discrete graphical models.

Low rank solvers #################################### benchmark/ : folder with the random instances used in the paper. ############################

1 Dec 08, 2022
The aim of this project is to build an AI bot that can play the Wordle game, or more generally Squabble

Wordle RL The aim of this project is to build an AI bot that can play the Wordle game, or more generally Squabble I know there are more deterministic

Aditya Arora 3 Feb 22, 2022
PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation

PocketNet This is the official repository of the paper: PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and M

Fadi Boutros 40 Dec 22, 2022
Official MegEngine implementation of CREStereo(CVPR 2022 Oral).

[CVPR 2022] Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation This repository contains MegEngine implementation of ou

MEGVII Research 309 Dec 30, 2022