United States

How to efficiently explore in reinforcement learning is an open problem. Many exploration algorithms employ the epistemic uncertainty of their own value predictions -- for instance to compute an exploration bonus or upper confidence bound. Unfortunately the required uncertainty is difficult to estimate in general with function approximation.

We propose epistemic value estimation (EVE): a recipe that is compatible with sequential decision making and with neural network function approximators. It equips agents with a tractable posterior over all their parameters from which epistemic value uncertainty can be computed efficiently.

We use the recipe to derive an epistemic Q-Learning agent and observe competitive performance on a series of benchmarks. Experiments confirm that the EVE recipe facilitates efficient exploration in hard exploration tasks.

AAAI 2023

Exploration via Epistemic Value Estimation

reinforcement learning algorithms

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Unsupervised/self-supervised graph neural networks (GNN) are vulnerable to inherent randomness in the input graph data which greatly affects the performance of the model in downstream tasks. In this paper, we alleviate the interference of graph randomness and learn appropriate representations of nodes without label information. To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy. We analyze the property of intrinsic connectivity and define intrinsic connectivity graph. We also identify the rank of the adjacency matrix as a crucial factor in revealing a graph that provides the same embeddings as the intrinsic connectivity graph. We then introduce structural entropy in the objective function to capture such a graph. Extensive experiments conducted on clustering and link prediction tasks under random-noises and meta-attack over three datasets show USER outperforms benchmarks and is robust to heavier randomness.

USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Every document in HRDoc has line-level annotations including categories and relations obtained from rule-based extractors and human annotators. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem. By adopting a multi-modal bidirectional encoder and a structure-aware GRU decoder with soft-mask operation, the DSPS model surpass the baseline method by a large margin. All scripts and datasets will be made publicly available at https://github.com/jfma-USTC/HRDoc.

HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures

Trustable explanations of machine learning (ML) models are vital in high-risk uses of artificial intelligence (AI). Apart from the computation of trustable explanations, a number of explainability queries have been identified and studied in recent work. Some of these queries involve solving quantification problems, either in propositional or in more expressive logics. This paper investigates one of these quantification problems, namely the feature membership problem (FMP), i.e. to decide whether a (possibly sensitive) feature can occur in some explanation of a prediction. In contrast with earlier work, that studied FMP for specific classifiers, this paper proposes a novel algorithm for the FMP quantification problem, that is applicable to any ML classifier. Furthermore, the paper shows that the novel algorithm is efficient in practice. The experimental results, obtained using random forests (RFs) induced from well-known publicly available datasets, demonstrate that the proposed solution outperforms existing state-of-the-art solvers for Quantified Boolean Formulas (QBF) by orders of magnitude. Finally, the paper also identifies a novel family of formulas that are challenging for currently state-of- the-art QBF solvers.


Solving Explainability Queries with Quantification: The Case of Feature Relevancy

We consider the problem of partitioning $n$ agents in an undirected social network into $k$ almost equal in size (differing by at most one) groups, where the utility of an agent for a group is the number of her neighbors in the group. The core and envy-freeness are two compelling axiomatic fairness guarantees in such settings. The former demands that there be no coalition of agents such that each agent in the coalition has more utility for that coalition than for her own group, while the latter demands that no agent envy another agent for the group they are in. We provide (often tight) approximations to both fairness guarantees, and many of our positive results are obtained via efficient algorithms. 

Partitioning Friends Fairly

The problem of image aesthetic quality assessment is surprisingly difficult to define precisely. Most early work attempted to estimate the average aesthetic rating of a group of observers, while some recent work has shifted to an approach based on few-shot personalization. In this paper, we connect few-shot personalization, via Immanuel Kant's concept of disinterested judgment, to an argument from feminist aesthetics about the biased tendencies of objective standards for subjective pleasures. To empirically investigate this philosophical debate, we introduce PR-AADB, a relabeling of the existing AADB dataset with labels for pairs of images, and measure how well the existing groundtruth predicts our new pairwise labels. We find, consistent with the feminist critique, that both the existing groundtruth and few-shot personalized predictions represent some users' preferences significantly better than others, but that it is difficult to predict when and for whom the existing groundtruth will be correct. We thus advise against using benchmark datasets to evaluate models for personalized IAQA, and recommend caution when attempting to account for subjective difference using machine learning more generally.

Correct for Whom? Subjectivity and the Evaluation of Personalized Image Aesthetics Assessment Models

Remarkable research efforts, e.g., regularization and architecture design, have been made to stabilize the training of the Generative Adversarial Networks (GANs). In contrast, we identify the instability can also come from the fragile balance at the early stage of adversarial learning. This paper proposes to warm up the model with a simple yet effective cooperative learning schedule, namely CoopInit, to learn a better starting point of GAN with very little computation overhead in training. In CoopInit, the discriminator is treated as an energy-based model and optimized via implicit maximum likelihood estimation (MLE). The discriminator immediately guides the generator's learning also with MLE. After such a quick warm-up, the training of GANs can seamlessly transit to the regular mini-max adversarial game and lead to better convergence. We demonstrate the effectiveness of the proposed approach over various GAN loss functions, model architectures and datasets. We improve the recorded FID on CIFAR-10 from 2.42 to 2.20 and IS from 10.14 to 10.20. We also propose to apply CoopInit in one-sided unpaired image translation and improve prior art.

CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning

Estimating the uncertainty in deep neural network predictions is crucial for many real-world applications. A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation. The chosen parametric form can be a poor fit to the data-generating distribution, resulting in unreliable uncertainty estimates. In this work, we propose SampleNet, a flexible and scalable architecture for modeling uncertainty that avoids specifying a parametric form on the output distribution. SampleNets do so by defining an empirical distribution using samples that are learned with the Energy Score and regularized with the Sinkhorn Divergence. SampleNets are shown to be able to well-fit a wide range of distributions and to outperform baselines on large-scale real-world regression tasks.

Estimating Regression Predictive Distributions with Sample Networks

The usage of deep neural networks in safety-critical systems is limited by our ability to guarantee their correct behavior. Runtime monitors are components aiming to identify unsafe predictions and discard them before they can lead to catastrophic consequences. Several recent works on runtime monitoring have focused on out-of-distribution (OOD) detection, i.e., identifying inputs that are different from the training data. In this work, we argue that OOD detection is not a well-suited framework to design efficient runtime monitors and that it is more relevant to evaluate monitors based on their ability to discard incorrect predictions. We call this setting out-of-model-scope detection and discuss the conceptual differences with OOD. We also conduct extensive experiments on popular datasets from the literature to show that studying monitors in the OOD setting can be misleading: 1. very good OOD results can give a false impression of safety, 2. comparison under the OOD setting does not allow identifying the best monitor to detect errors. Finally, we also show that removing erroneous training data samples helps to train better monitors.

Out-of-Distribution Detection Is Not All You Need

Automatic medical text simplification can assist providers with patient-friendly communication and make medical texts more accessible, thereby improving health literacy. But curating a quality corpus for this task requires the supervision of medical experts. In this work, we present Med-EASi (Medical dataset for Elaborative and Abstractive Simplification), a uniquely crowdsourced and finely annotated dataset for supervised simplification of short medical texts. Its expert-layman-AI collaborative annotations facilitate controllability over text simplification by marking four kinds of textual transformations: elaboration, replacement, deletion, and insertion. To learn medical text simplification, we fine-tune T5-large with four different styles of input-output combinations, leading to two control-free and two controllable versions of the model. We add two types of controllability into text simplification, by using a multi-angle training approach: position-aware, which uses in-place annotated inputs and outputs, and position-agnostic, where the model only knows the contents to be edited, but not their positions. Our results show that our fine-grained annotations improve learning compared to the unannotated baseline. Furthermore, our position-aware control enhances the model's ability to generate better simplification than the position-agnostic version. The data and code are available at https://github.com/Chandrayee/CTRL-SIMP.

Premium content

Exploration via Epistemic Value Estimation

Downloads

Next from AAAI 2023

USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

Similar lecture

H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES