United States

We study safe policy improvement (SPI) for partially observable Markov decision processes (POMDPs). SPI is an offline reinforcement learning (RL) problem that assumes access to (1) historical data about an environment, and (2) the so-called behavior policy that previously generated this data by interacting with the environment. SPI methods neither require access to a model nor the environment itself, and aim to reliably improve the behavior policy in an offline manner. Existing methods make the strong assumption that the environment is fully observable. In our novel approach to the SPI problem for POMDPs, we assume that a finite-state controller (FSC) represents the behavior policy and that finite memory is sufficient to derive optimal policies. This assumption allows us to map the POMDP to a finite-state fully observable MDP, the history MDP. We estimate this MDP by combining the historical data and the memory of the FSC, and compute an improved policy using an off-the-shelf SPI algorithm. The underlying SPI method constrains the policy-space according to the available data, such that the newly computed policy only differs from the behavior policy when sufficient data was available. We show that this new policy, converted into a new FSC for the (unknown) POMDP, outperforms the behavior policy with high probability. Experimental results on several well-established benchmarks show the applicability of the approach, even in cases where finite memory is not sufficient.

AAAI 2023

Safe Policy Improvement for POMDPs via Finite-State Controllers

planning with markov models (mdps

safe decision making under uncertainty

pomdps)

offline reinforcement learning

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

This paper presents a large anonymized dataset of homelessness alongside insights into the data-driven rehabilitation of homeless people. The dataset was gathered by a large non-profit organization working on rehabilitating the homeless for twenty years. This is the first dataset that we know of that contains rich information on thousands of homeless individuals seeking rehabilitation. We show how data analysis can help to make the rehabilitation of homeless people more effective and successful. Thus, we hope this paper alerts the data science community to the problem of homelessness. 

Rehabilitating Homeless: Dataset and Key Insights

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, especially for 3D volume data. Recent breakthroughs in self-supervised learning (SSL) offer the ability to overcome the lack of labeled training samples by learning feature representations from unlabeled data. However, most current SSL techniques in the medical field have been designed for either 2D images or 3D volumes. In practice, this restricts the capability to fully leverage unlabeled data from numerous sources, which may include both 2D and 3D data. Additionally, the use of these pre-trained networks is constrained to downstream tasks with compatible data dimensions.
In this paper, we propose a novel framework for unsupervised joint learning on 2D and 3D data modalities. Given a set of 2D images or 2D slices extracted from 3D volumes, we construct an SSL task based on a 2D contrastive clustering problem for distinct classes. The 3D volumes are exploited by computing vectored embedding at each slice and then assembling a holistic feature through deformable self-attention mechanisms in Transformer, allowing incorporating long-range dependencies between slices inside 3D volumes. These holistic features are further utilized to define a novel 3D clustering agreement-based SSL task and masking embedding prediction inspired by pre-trained language models. Experiments on downstream tasks, such as 3D brain segmentation, lung nodule detection, 3D heart structures segmentation, and abnormal chest X-ray detection, demonstrate the effectiveness of our joint 2D and 3D SSL approach. We improve plain 2D Deep-ClusterV2 and SwAV by a significant margin and also surpass various modern 2D and 3D SSL approaches.

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker's knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion attacks. However, attackers may not know what the model is used for in practice. We propose a generative adversarial network (GAN) based method to explore likely or similar domains of a target model -- the model domain inference (MDI) attack. For a given target (classification) model, we assume that the attacker knows nothing but the input and output formats and can use the model to derive the prediction for any input in the desired form. Our basic idea is to use the target model to affect a GAN training process for a candidate domain's dataset that is easy to obtain. We find that the target model may distort the training procedure less if the domain is more similar to the target domain. We then measure the distortion level with the distance between GAN-generated datasets, which can be used to rank candidate domains for the target model. Our experiments show that the auxiliary dataset from an MDI top-ranked domain can effectively boost the result of model-inversion attacks. 

GAN-based Domain Inference Attack

Traffic congestion event prediction is an important yet challenging task in intelligent transportation systems. Many existing works about traffic prediction integrate various temporal encoders and graph convolution networks (GCNs), called spatio-temporal graph-based neural networks, which focus on predicting dense variables such as flow, speed and demand in time snapshots, but they can hardly forecast the traffic congestion events that are sparsely distributed on the continuous time axis. In recent years, neural point process (NPP) has emerged as an appropriate framework for event prediction in continuous time scenarios. However, most conventional works about NPP cannot model the complex spatio-temporal dependencies and congestion evolution patterns. To address these limitations, we propose a spatio-temporal graph neural point process framework, named STGNPP for traffic congestion event prediction. Specifically, we first design the spatio-temporal graph learning module to fully capture the long-range spatio-temporal dependencies from the historical traffic state data along with the road network. The extracted spatio-temporal hidden representation and congestion event information are then fed into a continuous gated recurrent unit to model the congestion evolution patterns. In particular, to fully exploit the periodic information, we also improve the intensity function calculation of the point process with a periodic gated mechanism. Finally, our model simultaneously predicts the occurrence time and duration of the next congestion. Extensive experiments on two real-world datasets demonstrate that our method achieves superior performance in comparison to existing state-of-the-art approaches.

Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction

By harnessing the latest advances in deep learning, image-to-image translation architectures have recently achieved impressive capabilities. Unfortunately, the growing representational power of these architectures has prominent unethical uses. Among these, the threats of (1) face manipulation ("DeepFakes") used for misinformation or pornographic use (2) "DeepNude" manipulations of body images to remove clothes from individuals, etc. Several works tackle the task of disrupting such image translation networks by inserting imperceptible adversarial attacks into the input image. Nevertheless, these works have limitations that may result in disruptions that are not practical in the real world. Specifically, most works generate disruptions in a white-box scenario, assuming perfect knowledge about the image translation network. The few remaining works that assume a black-box scenario require a large number of queries to successfully disrupt the adversary's image translation network. In this work we propose Leaking Transferable Perturbations (LTP), an algorithm that significantly reduces the number of queries needed to disrupt an image translation network by dynamically re-purposing previous disruptions into new query efficient disruptions.

Practical Disruption of Image Translation Deepfake Networks

Accuracy and individual fairness are both crucial for trustworthy machine learning, but these two aspects are often incompatible with each other so that enhancing one aspect may sacrifice the other inevitably with side effects of true bias or false fairness. We propose in this paper a new fairness criterion, accurate fairness, to align individual fairness with accuracy. Informally, it requires the treatments of an individual and the individual's similar counterparts to conform to a uniform target, i.e., the ground truth of the individual. We prove that accurate fairness also implies typical group fairness criteria over a union of similar sub-populations. We then present a Siamese fairness in-processing approach to minimize the accuracy and fairness losses of a machine learning model under the accurate fairness constraints. To the best of our knowledge, this is the first time that a Siamese approach is adapted for bias mitigation. We also propose fairness confusion matrix-based metrics, fair-precision, fair-recall, and fair-F1 score, to quantify a trade-off between accuracy and individual fairness. Comparative case studies with popular fairness datasets show that our Siamese fairness approach can achieve on average 1.02%-8.78% higher individual fairness (in terms of fairness through awareness) and 8.38%-13.69% higher accuracy, as well as 10.09%-20.57% higher true fair rate, and 5.43%-10.01% higher fair-F1 score, than the state-of-the-art bias mitigation techniques. This demonstrates that our Siamese fairness approach can indeed improve individual fairness without trading accuracy. Finally, the accurate fairness criterion and Siamese fairness approach are applied to mitigate the possible service discrimination with a real Ctrip dataset, by on average fairly serving 112.33% more customers (specifically, 81.29% more customers in an accurately fair way) than baseline models.

Accurate Fairness: Improving Individual Fairness without Trading Accuracy

Non-Pharmaceutical Interventions (NPIs), such as social gathering restrictions, have shown effectiveness to slow the transmission of COVID-19 by reducing the contact of people. To support policy-makers, multiple studies have first modelled human mobility via macro indicators (e.g., average daily travel distance) and then study the effectiveness of NPIs. In this work, we focus on mobility modelling and, from a micro perspective, aim to predict locations that will be visited by COVID-19 cases. Since NPIs generally cause economic and societal loss, such a prediction benefits governments when they design and evaluate them. However, in real-world situations, strict privacy data protection regulations result in severe data sparsity problems (i.e., limited case and location information).
To address these challenges and jointly model variables including a geometric graph, a set of diffusions and a set of locations, we propose a model named Deep Graph Diffusion Infomax (DGDI). We show the maximization of DGDI can be bounded by two tractable components: a univariate Mutual Information (MI) between geometric graph and diffusion representation, and a univariate MI between diffusion representation and location representation. To facilitate the research of COVID-19 prediction, we present two benchmarks that contain geometric graphs and location histories of COVID-19 cases. Extensive experiments on the two benchmarks show that DGDI significantly outperforms other competing methods.

Human Mobility Modeling During the COVID-19 Pandemic via Deep Graph Diffusion Infomax

Counterfactuals are often described as 'retrospective,' focusing on hypothetical alternatives to a realized past. This description relates to an often implicit assumption about the structure and stability of exogenous variables in the system being modeled –– an assumption that is reasonable in many settings where counterfactuals are used. In this work, we consider cases where we might reasonably make a different assumption about exogenous variables, namely, that the exogenous noise terms of each unit do exhibit some unit-specific structure and/or stability. This leads us to a different use of counterfactuals — a 'forward-looking' rather than 'retrospective' counterfactual. We introduce "counterfactual treatment choice," a type of treatment choice problem that motivates using forward-looking counterfactuals. We then explore how mismatches between interventional versus forward-looking counterfactual approaches to treatment choice, consistent with different assumptions about exogenous noise, can lead to counterintuitive results.

Counterfactuals for the Future

AI systems can create, propagate, support, and automate bias in decision-making processes. To mitigate biased decisions, we both need to understand the origin of the bias and define what it means for an algorithm to make fair decisions. Most group fairness notions assess a model's equality of outcome by computing statistical metrics on the outputs. We argue that these output metrics encounter intrinsic obstacles and present a complementary approach that aligns with the increasing focus on equality of treatment. By Locating Unfairness through Canonical Inverse Design (LUCID), we generate a canonical set that shows the desired inputs for a model given a preferred output. The canonical set reveals the model's internal logic and exposes potential unethical biases by repeatedly interrogating the decision-making process. We evaluate LUCID on the UCI Adult and COMPAS data sets and find that some biases detected by a canonical set differ from those of output metrics. The results show that by shifting the focus towards equality of treatment and looking into the algorithm's internal workings, the canonical sets are a valuable addition to the toolbox of algorithmic fairness evaluation.



LUCID: Exposing Bias through Inverse Design

Access to high-quality maternal health care services is limited in Kenya, which resulted in ∼36,000 maternal and neonatal deaths in 2018. To tackle this challenge, Jacaranda Health (a non-profit organization working on maternal health in Kenya) developed PROMPTS, an SMS based tele-triage system for pregnant and puerperal women, which has more than 350,000 active users in Kenya. PROMPTS empowers pregnant women living far away from doctors and hospitals to send SMS messages to get quick answers (through human helpdesk agents) to questions about their medical symptoms and pregnancy status. Unfortunately, ∼1.1 million SMS messages are received by PROMPTS every month, which makes it challenging for helpdesk agents to ensure that these messages can be interpreted correctly and evaluated by their level of emergency to ensure timely responses and/or treatments for women in need. This paper reports on a collaborative effort with Jacaranda Health to develop a state-of-the-art natural language processing (NLP) framework, TRIM-AI (TRIage for Mothers using AI), which can automatically predict the emergency level (or severity of medical condition) of a pregnant mother based on the content of their SMS messages. TRIM-AI leverages recent advances in multi-lingual pre-training and continual pre-training to tackle code-mixed SMS messages (between English and Swahili), and achieves a weighted F1 score of 0.774 on real-world datasets. TRIMAI has been successfully deployed in the field since June 2022, and is being used by Jacaranda Health to prioritize the provision of services and care to pregnant women with the most critical medical conditions. Our preliminary A/B tests in the field show that TRIM-AI is ∼17% more accurate at predicting high-risk medical conditions from SMS messages sent by pregnant Kenyan mothers, which reduces the helpdesk’s workload by ∼12%.

Premium content

Safe Policy Improvement for POMDPs via Finite-State Controllers

Downloads

Next from AAAI 2023

Rehabilitating Homeless: Dataset and Key Insights

Similar lecture

On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples