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.
Object detection evaluation metrics using Python.

Object detection evaluation metrics using Python.

Louis Facun 2 Sep 06, 2022
A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband Items

A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband Items This repository co

Taimur Hassan 3 Mar 16, 2022
SNIPS: Solving Noisy Inverse Problems Stochastically

SNIPS: Solving Noisy Inverse Problems Stochastically This repo contains the official implementation for the paper SNIPS: Solving Noisy Inverse Problem

Bahjat Kawar 35 Nov 09, 2022
Official PyTorch implementation of paper: Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation (ICCV 2021 Oral Presentation)

SML (ICCV 2021, Oral) : Official Pytorch Implementation This repository provides the official PyTorch implementation of the following paper: Standardi

SangHun 61 Dec 27, 2022
Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models Abstract Many applications of generative models rely on the marginali

Stanford Intelligent Systems Laboratory 9 Jun 06, 2022
TCube generates rich and fluent narratives that describes the characteristics, trends, and anomalies of any time-series data (domain-agnostic) using the transfer learning capabilities of PLMs.

TCube: Domain-Agnostic Neural Time series Narration This repository contains the code for the paper: "TCube: Domain-Agnostic Neural Time series Narrat

Mandar Sharma 7 Oct 31, 2021
Using modified BiSeNet for face parsing in PyTorch

face-parsing.PyTorch Contents Training Demo References Training Prepare training data: -- download CelebAMask-HQ dataset -- change file path in the pr

zll 1.6k Jan 08, 2023
Train a deep learning net with OpenStreetMap features and satellite imagery.

DeepOSM Classify roads and features in satellite imagery, by training neural networks with OpenStreetMap (OSM) data. DeepOSM can: Download a chunk of

TrailBehind, Inc. 1.3k Nov 24, 2022
This is a Deep Leaning API for classifying emotions from human face and human audios.

Emotion AI This is a Deep Leaning API for classifying emotions from human face and human audios. Starting the server To start the server first you nee

crispengari 5 Oct 02, 2022
3D AffordanceNet is a 3D point cloud benchmark consisting of 23k shapes from 23 semantic object categories, annotated with 56k affordance annotations and covering 18 visual affordance categories.

3D AffordanceNet This repository is the official experiment implementation of 3D AffordanceNet benchmark. 3D AffordanceNet is a 3D point cloud benchma

49 Dec 01, 2022
Source code for 2021 ICCV paper "In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces"

In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces This is the PyTorch implementation for 2021 ICCV paper "In-the-Wild Single C

27 Dec 06, 2022
An off-line judger supporting distributed problem repositories

Thaw 中文 | English Thaw is an off-line judger supporting distributed problem repositories. Everyone can use Thaw release problems with license on GitHu

countercurrent_time 2 Jan 09, 2022
Lenia - Mathematical Life Forms

For full version list, see Timeline in Lenia portal [2020-10-13] Update Python version with multi-kernel and multi-channel extensions (v3.4 LeniaNDK.p

Bert Chan 3.1k Dec 28, 2022
Large dataset storage format for Pytorch

H5Record Large dataset ( 100G, = 1T) storage format for Pytorch (wip) Support python 3 pip install h5record Why? Writing large dataset is still a

theblackcat102 43 Oct 22, 2022
[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data (NeurIPS 2021) This repository will provide the official PyTorch implementa

Liming Jiang 238 Nov 25, 2022
SpecAugmentPyTorch - A Pytorch (support batch and channel) implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

SpecAugment An implementation of SpecAugment for Pytorch How to use Install pytorch, version=1.9.0 (new feature (torch.Tensor.take_along_dim) is used

IMLHF 3 Oct 11, 2022
Improving Machine Translation Systems via Isotopic Replacement

CAT (Improving Machine Translation Systems via Isotopic Replacement) Machine translation plays an essential role in people’s daily international commu

Zeyu Sun 10 Nov 30, 2022
Code and data for "Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning" (EMNLP 2021).

GD-VCR Code for Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning (EMNLP 2021). Research Questions and Aims: How well can a model perform o

Da Yin 24 Oct 13, 2022
PyTorch implementation of "PatchGame: Learning to Signal Mid-level Patches in Referential Games" to appear in NeurIPS 2021

PatchGame: Learning to Signal Mid-level Patches in Referential Games This repository is the official implementation of the paper - "PatchGame: Learnin

Kamal Gupta 22 Mar 16, 2022
Official code for 'Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning' [ICCV 2021]

RTFM This repo contains the Pytorch implementation of our paper: Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Lear

Yu Tian 242 Jan 08, 2023