Canada

One of the major challenges of offline reinforcement learning (RL) is dealing with distribution shifts that stem from the mismatch between the trained policy and the data collection policy. Stationary distribution correction estimation algorithms (DICE) have addressed this issue by regularizing the policy optimization with f-divergence between the state-action visitation distributions of the data collection policy and the optimized policy. While such regularization naturally integrates to derive an objective to get optimal state-action visitation, such an implicit policy optimization framework has shown limited performance in practice. We observe that the reduced performance is attributed to the biased estimate and the properties of conjugate functions of f-divergence regularization. In this paper, we improve the regularized implicit policy optimization framework by relieving the bias and reshaping the conjugate function by relaxing the constraints. We show that the relaxation adjusts the degree of involvement of the sub-optimal samples in optimization, and we derive a new offline RL algorithm that benefits from the relaxed framework, improving from a previous implicit policy optimization algorithm by a large margin.

AAAI 2024

Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization

ml: reinforcement learning theory

ml: optimization

ml: reinforcement learning algorithms

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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. 

Graph matching is a fundamental problem in pattern recognition, with many applications such as software analysis and computational biology. One well-known type of graph matching problem is graph isomorphism, which consists of deciding if two graphs are identical. Despite its usefulness, the properties that one may check using graph isomorphism are rather limited, since it only allows strict equality checks between two graphs. For example, it does not allow one to check complex structural properties such as if the target graph is an arbitrary length sequence followed by an arbitrary size loop.

We propose a generalization of graph isomorphism that allows one to check such properties through a declarative specification. This specification is given in the form of a Regular Graph Pattern (ReGaP), a special type of graph, inspired by regular expressions, that may contain wildcard nodes that represent arbitrary structures such as variable-sized sequences or subgraphs. We propose a SAT-based algorithm for checking if a target graph matches a given ReGaP. We also propose a preprocessing technique for improving the performance of the algorithm and evaluate it through an extensive experimental evaluation on benchmarks from the CodeSearchNet dataset.

SAT-Based Algorithms for Regular Graph Pattern Matching | VIDEO

In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end generative GZSL framework called D$^3$GZSL. This framework respects seen and synthesized unseen data as in-distribution and out-of-distribution data, respectively, for a more balanced model. D$^3$GZSL comprises two core modules: in-distribution dual space distillation (ID$^2$SD) and out-of-distribution batch distillation (O$^2$DBD). ID$^2$SD aligns teacher-student outcomes in embedding and label spaces, enhancing learning coherence. O$^2$DBD introduces low-dimensional out-of-distribution representations per batch sample, capturing shared structures between seen and unseen categories. Our approach demonstrates its effectiveness across established GZSL benchmarks, seamlessly integrating into mainstream generative frameworks. Extensive experiments consistently showcase that D$^3$GZSL elevates the performance of existing generative GZSL methods, underscoring its potential to refine zero-shot learning practices.The code is available at: https://github.com/PJBQ/D3GZSL.git

Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition | VIDEO

As responsible AI gains importance in machine learning algorithms, properties like fairness, adversarial robustness, and causality have received considerable attention in recent years. However, despite their individual significance, there remains a critical gap in simultaneously exploring and integrating these properties. In this paper, we propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models (SCMs) in heterogeneous data spaces, particularly when dealing with discrete sensitive attributes. We use SCMs and sensitive attributes to create a fair metric and apply it to measure semantic similarity among individuals. By introducing a novel causal adversarial perturbation (CAP) and applying adversarial training, we create a new regularizer that combines individual fairness, causality, and robustness in the classifier. Our method is evaluated on both real-world and synthetic datasets, demonstrating its effectiveness in achieving an accurate classifier that simultaneously exhibits fairness, adversarial robustness, and causal awareness.

Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces | VIDEO

Federated learning (FL) has emerged as a promising collaborative and secure paradigm for training a model from decentralized data without compromising privacy. Group fairness and client fairness are two dimensions of fairness that are important for FL. Standard FL can result in disproportionate disadvantages for certain clients, and it still faces the challenge of treating different groups equitably in a population. The problem of privately training fair FL models without compromising the generalization capability of disadvantaged clients remains open. In this paper, we propose a method, called mFairFL, to address this problem and achieve group fairness and client fairness simultaneously. mFairFL leverages differential multipliers to construct an optimization objective for empirical risk minimization with fairness constraints. Before aggregating locally trained models, it first detects conflicts among their gradients, and then iteratively curates the direction and magnitude of gradients to mitigate these conflicts. Theoretical analysis proves mFairFL facilitates the fairness in model development. The experimental evaluations based on three benchmark datasets show significant advantages of mFairFL compared to seven state-of-the-art baselines.

Multi-Dimensional Fair Federated Learning

Probabilistic circuits (PCs) such as sum-product networks efficiently represent large multi-variate probability distributions. They are preferred in practice over other probabilistic representations, such as Bayesian and Markov networks, because PCs can solve marginal inference (MAR) tasks in time that scales linearly in the size of the network. Unfortunately, the most probable explanation (MPE) task and its generalization, the marginal maximum-a-posteriori (MMAP) inference task remain NP-hard in these models. Inspired by the recent work on using neural networks for generating near-optimal solutions to optimization problems such as integer linear programming, we propose an approach that uses neural networks to approximate MMAP inference in PCs. The key idea in our approach is to approximate the cost of an assignment to the query variables using a continuous multilinear function and then use the latter as a loss function. The two main benefits of our new method are that it is self-supervised, and after the neural network is learned, it requires only linear time to output a solution. We evaluate our new approach on several benchmark datasets and show that it outperforms three competing linear time approximations: max-product inference, max-marginal inference, and sequential estimation, which are used in practice to solve MMAP tasks in PCs.

Neural Network Approximators for Marginal MAP in Probabilistic Circuits | VIDEO

Stochastic Boolean satisfiability (SSAT) is a natural formalism for optimization under uncertainty. Its decision version implicitly imposes a final threshold quantification on an SSAT formula. However, the single threshold quantification restricts the expressive power of SSAT. In this work, we enrich SSAT with an additional threshold quantifier, resulting in a new formalism SSAT($\Theta$). The increased expressiveness allows SSAT($\Theta$), which remains in the PSPACE complexity class, to subsume and encode the languages in the counting hierarchy. An SSAT($\Theta$) solver, ClauSSat($\Theta$), is developed. Experiments show the applicability of the solver in uniquely solving complex SSAT($\Theta$) instances of parameter synthesis and SSAT extension.

Unifying Decision and Function Queries in Stochastic Boolean Satisfiability

Mechanism design on social networks has attracted extensive attention recently. The goal is to design mechanisms to incentivize participants to invite more participants via their social networks, and the challenge is that the participants are competitors. Various mechanisms have been proposed for single-/multiple-unit auctions, but it has been shown that it is challenging to design such mechanisms for more complex settings. We move this forward to investigate a double auction on a network where each trader (a buyer or a seller) can link to other buyers and sellers. Incentiving invitation is more difficult than in multi-unit one-sided auctions, because there are two different roles and a buyer (seller) seems happy to invite a seller (buyer), but again the invited seller (buyer) may invite another buyer (seller) to compete with the original buyer (seller). To combat this, we propose a solution called dynamic trade reduction (DTR), which also guarantees a non-negative revenue for the market owner. Interestingly, our solution is also applicable to the multi-unit one-sided auction when there is only one seller linking to only buyers on the network. We believe that the principle of our solution has the potential to be extended to design the multi-item one-sided auction.

Double Auction on Diffusion Network

Researchers building behavioral models, such as behavioral game theorists, use experimental data to evaluate predictive models of human behavior. However, there is little agreement about which loss function should be used in evaluations, with error rate, negative log-likelihood, cross-entropy, Brier score, and squared L2 error all being common choices. We attempt to offer a principled answer to the question of which loss functions should be used for this task, formalizing axioms that we argue loss functions should satisfy. We construct a family of loss functions, which we dub ``diagonal bounded Bregman divergences'', that satisfy all of these axioms. These rule out many loss functions used in practice, but notably include squared L2 error; we thus recommend its use for evaluating behavioral models.

How to Evaluate Behavioral Models

With the advancement and utility of Artificial Intelligence (AI), personalising education to a global population could be a cornerstone of new educational systems in the future. This work presents the PEEKC dataset and the TrueLearn Python library, which contains a dataset and a series of online learner state models that are essential to facilitate research on learner engagement modelling. TrueLearn family of models was designed following the "open learner" concept, using humanly-intuitive user representations. This family of scalable, online models also help end-users visualise the learner models, which may in the future facilitate user interaction with their models/recommenders. The extensive documentation and coding examples make the library highly accessible to both machine learning developers and educational data mining and learning analytics practitioners. The experiments show the utility of both the dataset and the library with predictive performance significantly exceeding comparative baseline models. The dataset contains a large amount of AI-related educational videos, which are of interest for building and validating AI-specific educational recommenders.

A Toolbox for Modelling Engagement with Educational Videos

Sentiment analysis provides a promising tool to automatically assess the emotions voiced in written student feedback such as periodically collected unit-of-study reflections. The commonly used dictionary-based approaches are limited to major languages and fail to capture contextual differences.  Pretrained large language models have been shown to be biased and online versions raise privacy concerns. Hence, we resort to traditional supervised machine learning (ML) approaches which are designed to overcome these issues by learning from domain-specific labeled data. However, these labels are hard to come by -- in our case manually annotating student feedback is prone to bias and time-consuming, especially in high-enrollment courses. In this work, we investigate the use of student crowdsourced labels for supervised sentiment analysis for education. Specifically, we compare crowdsourced and student self-reported labels with human expert annotations and use them in various ML approaches to evaluate the performance on predicting emotions of written student feedback collected from large computer science classes. We find that the random forest model trained with student-crowdsourced labels tremendously improves the identification of reflections with negative sentiment.  In addition to our quantitative study, we describe our crowdsourcing experiment which was intentionally designed to be an educational activity in an introduction to data science course.

Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization

Downloads

Next from AAAI 2024

SAT-Based Algorithms for Regular Graph Pattern Matching | VIDEO

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES