United States

Formulating a real-world problem under the Reinforcement
Learning framework involves non-trivial design choices, such
as selecting a discount factor for the learning objective (dis-
counted cumulative rewards), which articulates the planning
horizon of the agent. This work investigates the impact of the
discount factor on the bias-variance trade-off given structural
parameters of the underlying Markov Decision Process. Our
results support the idea that a shorter planning horizon might
be beneficial, especially under partial observability.

AAAI 2025

On Shallow Planning Under Partial Observability

reinforcement learning

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 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.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/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. AAAI-25 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.



Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.

ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data

Personalized federated learning (PFL) has recently gained significant attention for its capability to address the poor convergence performance on highly heterogeneous data and the lack of personalized solutions of traditional federated learning (FL). Existing mainstream approaches either perform personalized aggregation based on a specific model architecture to leverage global knowledge or achieve personalization by exploiting client similarities. However, the former overlooks the discrepancies in client data distributions by indiscriminately aggregating all clients, while the latter lacks fine-grained collaboration of classifiers relevant to local tasks. In view of this challenge, we propose a Personalized Federated learning method for Enhancing Collaboration among Similar Classifiers (PFedCS), which aims at improving the client’s accuracy on local tasks. Concretely, it is achieved by leveraging awareness of the client classifier similarities to address the above problems. By iteratively measuring the distance of the classifier parameters between clients and clustering with each client as a cluster center, the central server adaptively identifies the collaborating clients with similar data distributions. In addition, a distance-constrained aggregation method is designed to generate customized collaborative classifiers to guide local training. As a result, extensive experimental evaluations conducted on three datasets demonstrate that our method achieves state-of-the-art performance.

PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers

Classical planning asks for a sequence of operators reaching a given goal. While the most common case is to compute a plan, many scenarios require more than that. However, quantitative reasoning on the plan space remains mostly unexplored. A fundamental problem is to count plans, which relates to the conditional probability on the plan space. Indeed, qualitative and quantitative approaches are well-established in various other areas of automated reasoning. 

We present the first study to quantitative and qualitative reasoning on the plan space. In particular, we focus on polynomially bounded plans. On the theoretical side, we study its complexity, which gives rise to rich reasoning modes. Since counting is hard in general, we introduce the easier notion of facets, which enables understanding the significance of operators. On the practical side, we implement quantitative reasoning for planning. Thereby, we transform a planning task into a propositional formula and use knowledge compilation to count different plans. This framework scales well to large plan spaces, while enabling rich reasoning capabilities such as learning pruning functions and explainable planning.

Counting and Reasoning with Plans

Uncertainty quantification remains a difficult challenge in reinforcement learning. Several algorithms exist that successfully quantify uncertainty in a practical setting. However it is unclear whether these algorithms are theoretically sound and can be expected to converge. Further, they seem to treat the uncertainty in the target parameters in different ways. In this work, we unify several practical algorithms into one theoretical framework by defining a new Bellman operator on distributions, and show that this Bellman operator is a contraction. We highlight use cases of our framework by analyzing an existing Bayesian Q-learning algorithm, and also introduce a novel uncertainty-aware variant of PPO that adaptively sets its clipping hyperparameter.

Epistemic Bellman Operators

Algebraic model counting unifies many inference tasks on logic formulas by exploiting semirings. Rather than focusing on inference, we consider learning, especially in statistical-relational and neurosymbolic AI, which combine logical, probabilistic and neural representations. Concretely, we show that the very same semiring perspective of algebraic model counting also applies to learning.  This allows us to unify various learning algorithms by generalizing gradients and backpropagation to different semirings. Furthermore, we show how cancellation and ordering properties of a semiring can be exploited for more memory-efficient backpropagation. This allows us to obtain some interesting variations of state-of-the-art gradient-based optimisation methods for probabilistic logical models. We also discuss why algebraic model counting on tractable circuits does not lead to more efficient second-order optimization. Empirically, our algebraic backpropagation exhibits considerable speed-ups as compared to existing approaches.

The Gradient of Algebraic Model Counting

Trajectory-user linking (TUL) aims to match anonymous trajectories to the most likely users who generated them, offering benefits for a wide range of real-world spatio-temporal applications. However, existing TUL methods are limited by high model complexity and poor learning of the effective representations of trajectories, rendering them ineffective in handling large-scale user trajectory data.In this work, we propose a novel Scalable Trajectory-User Linking with dual-stream representation networks for large-scale TUL problem, named ScaleTUL Specifically, ScaleTUL generates two views using temporal and spatial augmentations to exploit supervised contrastive learning framework to effectively capture the irregularities of trajectories. In each view, a dual-stream trajectory encoder consisting of a long-term encoder and a short-term encoder is designed to learn the unified representations of trajectories that fuses different temporal-spatial dependencies. Then, a TUL layer is used to associate the trajectories with the corresponding users in the representation space using a two-stage training model.Experimental results on check-in mobility datasets from three real-world cities and the nationwide U.S. demonstrate the superiority of ScaleTUL over state-of-the-art baselines for large-scale TUL tasks. The source code of our model is available at https://anonymous.4open.science/r/Code-7EB4.

Scalable Trajectory-User Linking with Dual-Stream Representation Networks

Businesses employ third-party Large Language Models (LLMs), which raises substantial privacy issues due to the risk of exposing sensitive prompts. To mitigate, this paper introduces Portcullis, a privacy-preserving gateway service designed to protect users' sensitive information transparently and reliably, while maintaining the efficiency and accuracy of responses from third-party LLMs.

Portcullis functions as a mediator, anonymizing sensitive data in prompts, securely interacting with the LLM, and accurately reconstructing responses. It ensures all data processing occurs within secure encrypted memory. Additionally, the entire gateway is fully attested to verify its trustworthiness and guarantee that user privacy remains uncompromised. Portcullis is the first of its kind, offering a verifiable and scalable privacy gateway for third-party LLM inferences.


We assess Portcullis's efficiency as a confidential container platform, demonstrating that its startup time scales linearly, ensuring scalability. Additionally, we evaluate its runtime performance using the PII and Enron Email Dataset. For masking and unmasking workloads, Portcullis outperforms Hide-and-Seek by 96x speed up, while maintaining equal or better false positive and false negative rates compared to existing solutions. On the Enron dataset, Portcullis achieves notably higher accuracy, surpassing Hide-and-Seek by over 0.1 for GPT-4o mini.

Portcullis: A Scalable and Verifiable Privacy Gateway for Third-Party LLM Inference

Reliable failure detection holds paramount importance in safety-critical applications.
Yet, neural networks are known to produce overconfident predictions for misclassified samples. 
As a result, it remains a problematic matter as existing confidence score functions rely on category-level signals, the logits, to detect failures. 
This research introduces an innovative strategy, leveraging human-level concepts for a dual purpose: to reliably detect $\textit{when}$ a model fails and to transparently interpret $\textit{why}$.
By integrating a nuanced array of signals for each category, our method enables a finer-grained assessment of the model's confidence.
We present a simple yet highly effective approach based on the ordinal ranking of concept activation to the input image. 
Without bells and whistles, our method is able to significantly reduce the false positive rate across diverse real-world image classification benchmarks, specifically by $3.7$% on $\textit{ImageNet}$ and $9.0$% on $\textit{EuroSAT}$.

Interpretable Failure Detection with Human-Level Concepts

The accurate assessment of sperm morphology is crucial in andrological diagnostics, where the segmentation of sperm images presents significant challenges. Existing approaches frequently rely on large annotated datasets and often struggle with the segmentation of overlapping sperm and the presence of dye impurities. To address these challenges, this paper first analyzes the issue of overlapping sperm tails from a geometric perspective and introduces a novel clustering algorithm, Con2Dis, which effectively segments overlapping tails by considering three essential factors: CONnectivity, CONformity, and DIStance. Building on this foundation, we propose an unsupervised method, SpeHeaTal, designed for the comprehensive segmentation of the SPErm HEAd and TAiL. SpeHeaTal employs the Segment Anything Model (SAM) to generate masks for sperm heads while filtering out dye impurities, utilizes Con2Dis to segment tails, and then applies a tailored mask splicing technique to produce complete sperm masks. Experimental results underscore the superior performance of SpeHeaTal, particularly in handling images with overlapping sperm.

SpeHeaTal: A Cluster-Enhanced Segmentation Method for Sperm Morphology Analysis

The strategic behavior of users is significantly influenced by their hidden information such as private valuations, risk preferences, and price sensitivities. Contextual behavioral model learning refers to learning the dependence of users' hidden information on their observable context information. While many existing studies use offline data to learn contextual behavioral models, we study how to design sequential experiments to collect the most informative user behavioral data for learning. We propose a basic inference-then-design method. In each experimental period, it infers a probabilistic contextual behavioral model using historical experimental data, and then designs the new experiment to maximize the gain of information about the probabilistic model. We further improve the basic method in two aspects. First, we improve the inference step by specifying a more informative prior for learning the probabilistic contextual behavioral model. Second, we integrate the inference and design steps instead of conducting them separately. Our rigorous theoretic analysis reveals that the optimization objective of the inference step can be modified to account for the downstream experimental design step. Numerical experiments show that our methods lead to more effective experiments, i.e., the collected experimental data can help in learning a more accurate behavioral model.

Downloads

Next from AAAI 2025

ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data

Similar lecture

Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods