亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

圖是一種普遍存在的數據類型，出現在許多現實世界的應用中，包括社會網絡分析、建議和財務安全。盡管這很重要，但幾十年的研究已經發展出了豐富的計算模型來挖掘圖表。盡管它很繁榮，但最近對潛在的算法歧視的擔憂有所增長。圖上的算法公平性是一個有吸引力但又具有挑戰性的研究課題，它旨在減輕圖挖掘過程中引入或放大的偏差。第一個挑戰對應于理論挑戰，圖數據的非IID性質不僅可能使許多現有公平機器學習研究背后的基本假設失效，而且還可能基于節點之間的相互關聯而不是現有公平機器學習中的公平定義引入新的公平定義。第二個挑戰是關于算法方面的，目的是理解如何在模型準確性和公平性之間取得平衡。本教程旨在(1) 全面回顧最先進的技術，以加強圖的算法公平，(2) 啟發開放的挑戰和未來的方向。我們相信本教程可以使數據挖掘、人工智能和社會科學領域的研究人員和從業者受益。 //jiank2.web.illinois.edu/tutorial/kdd22/algofair_on_graphs.html

Introduction

Background and motivations * Problem definitions and settings * Key challenges * Part I: Group Fairness on Graphs

Fair graph ranking * Fair graph clustering * Fair graph embedding * Part II: Individual Fairness on Graphs

Optimization-based method * Ranking-based method * Part III: Other Fairness on Graphs

Counterfactual fairness * Degree-related fairness * Part IV: Beyond Fairness on Graphs

Related problems * Explainability * Accountability * Robustness * Part V: Future Trends

Fairness on dynamic graphs * Benchmark and evaluation metrics * Fairness vs. other social aspects

在當今日益互聯的世界，圖挖掘在許多現實世界的應用領域發揮著關鍵作用，包括社交網絡分析、建議、營銷和金融安全。人們作出了巨大的努力來發展廣泛的計算模型。然而，最近的研究表明，許多被廣泛應用的圖挖掘模型可能會受到潛在的歧視。圖挖掘的公平性旨在制定策略以減少挖掘過程中引入或放大的偏差。在圖挖掘中加強公平性的獨特挑戰包括: (1)圖數據的非iid性質的理論挑戰，這可能會使許多現有研究背后的公平機器學習的基本假設無效，(2) 算法挑戰平衡模型準確性和公平性的困境。本教程旨在(1)全面回顧圖挖掘方面最先進的技術，(2)確定有待解決的挑戰和未來的趨勢。特別是，我們首先回顧了背景、問題定義、獨特的挑戰和相關問題;然后，我們將重點深入概述(1)在圖挖掘背景下實施群體公平、個人公平和其他公平概念的最新技術，以及(2)圖上算法公平的未來研究方向。我們相信，本教程對數據挖掘、人工智能、社會科學等領域的研究人員和實踐者具有吸引力，并對現實世界的眾多應用領域有益。

//jiank2.web.illinois.edu/tutorial/cikm21/fair_graph_mining.html

能夠解釋機器學習模型的預測在醫療診斷或自主系統等關鍵應用中是很重要的。深度非線性ML模型的興起，在預測方面取得了巨大的進展。然而，我們不希望如此高的準確性以犧牲可解釋性為代價。結果，可解釋AI (XAI)領域出現了，并產生了一系列能夠解釋復雜和多樣化的ML模型的方法。

在本教程中，我們結構化地概述了在深度神經網絡(DNNs)的背景下為XAI提出的基本方法。特別地，我們提出了這些方法的動機，它們的優點/缺點和它們的理論基礎。我們還展示了如何擴展和應用它們，使它們在現實場景中發揮最大的作用。

本教程針對的是核心和應用的ML研究人員。核心機器學習研究人員可能會有興趣了解不同解釋方法之間的聯系，以及廣泛的開放問題集，特別是如何將XAI擴展到新的ML算法。應用ML研究人員可能會發現，理解標準驗證程序背后的強大假設是很有趣的，以及為什么可解釋性對進一步驗證他們的模型是有用的。他們可能還會發現新的工具來分析他們的數據并從中提取見解。參與者將受益于技術背景(計算機科學或工程)和基本的ML訓練。

目錄內容：

Part 1: Introduction to XAI (WS) 可解釋人工智能

• Motivations for XAI
• Methods and Validation of XAI
• The Clever Hans Effect

Part 2: Methods for Explaining DNNs (GM) 可解釋深度神經網絡方法

• Self-Explainable DNNs
• Perturbation-Based Explanation Techniques
• Propagation-Based Explanation Techniques

Part 3: Implementation, Theory, Evaluation, Extensions (GM) 實現，理論、評價

• Implementating XAI Techniques for DNNs
• Theoretical Embedding of XAI
• Desiderata of XAI Techniques and Evaluation
• Extending XAI Beyond Heatmaps and DNNs

Part 4: Applications (WS) 應用

• Walk-Through Examples
• Debugging Large Datasets (Meta-Explanations and "Unhansing")
• XAI in the Sciences

The tutorial is written for those who would like an introduction to reinforcement learning (RL). The aim is to provide an intuitive presentation of the ideas rather than concentrate on the deeper mathematics underlying the topic. RL is generally used to solve the so-called Markov decision problem (MDP). In other words, the problem that you are attempting to solve with RL should be an MDP or its variant. The theory of RL relies on dynamic programming (DP) and artificial intelligence (AI). We will begin with a quick description of MDPs. We will discuss what we mean by “complex” and “large-scale” MDPs. Then we will explain why RL is needed to solve complex and large-scale MDPs. The semi-Markov decision problem (SMDP) will also be covered.

The tutorial is meant to serve as an introduction to these topics and is based mostly on the book: “Simulation-based optimization: Parametric Optimization techniques and reinforcement learning” [4]. The book discusses this topic in greater detail in the context of simulators. There are at least two other textbooks that I would recommend you to read: (i) Neuro-dynamic programming [2] (lots of details on convergence analysis) and (ii) Reinforcement Learning: An Introduction [11] (lots of details on underlying AI concepts). A more recent tutorial on this topic is [8]. This tutorial has 2 sections: ? Section 2 discusses MDPs and SMDPs. ? Section 3 discusses RL. By the end of this tutorial, you should be able to ? Identify problem structures that can be set up as MDPs / SMDPs. ? Use some RL algorithms.

Deep Learning in Computer Vision: Methods, Interpretation, Causation, and Fairness Deep learning models have succeeded at a variety of human intelligence tasks and are already being used at commercial scale. These models largely rely on standard gradient descent optimization of function parameterized by , which maps an input to an output . The optimization procedure minimizes the loss (difference) between the model output and actual output . As an example, in the cancer detection setting, is an MRI image, and is the presence or absence of cancer. Three key ingredients hint at the reason behind deep learning’s power: (1) deep architectures that are adept at breaking down complex functions into a composition of simpler abstract parts; (2) standard gradient descent methods that can attain local minima on a nonconvex Loss function that are close enough to the global minima; and (3) learning algorithms that can be executed on parallel computing hardware (e.g., graphics processing units), thus making the optimization viable over hundreds of millions of observations . Computer vision tasks, where the input is a high-dimensional image or video, are particularly suited to deep learning application. Recent advances in deep architectures (i.e., inception modules, attention networks, adversarial networks and DeepRL) have opened up completely new applications that were previously unexplored. However, the breakneck progress to replace human tasks with deep learning comes with caveats. These deep models tend to evade interpretation, lack causal relationships between input and output , and may inadvertently mimic not just human actions but also human biases and stereotypes. In this tutorial, we provide an intuitive explanation of deep learning methods in computer vision as well as limitations in practice.