United States

Offline reinforcement methods (RL) aim to learn optimal policies with access only to trajectories in a fixed dataset. Policy constraint methods formulate policy learning as an optimization problem that balances maximizing reward with minimizing deviation from the behavior policy. Closed form solutions to this problem can be derived as weighted behavioral cloning objectives that, in theory, must compute an intractable partition function. Reinforcement learning has gained popularity in language modeling to align models with human preferences; some recent works consider paired completions that are ranked by a preference model following which the likelihood of the preferred completion is directly increased. We adapt this approach of paired comparison. By reformulating the paired-sample optimization problem, we fit the maximum-mode of the Q function while maximizing behavioral consistency of policy actions. This yields our algorithm, Behavior Preference Regression for offline RL (BPR). We empirically evaluate BPR on the widely used D4RL Locomotion and Antmaze datasets, as well as the more challenging V-D4RL suite, which operates in image-based state spaces. BPR demonstrates state-of-the-art performance over all domains. Our on-policy experiments suggest that BPR takes advantage of the stability of on-policy value functions with minimal performance degradation on Locomotion datasets.

AAAI 2025

Behaviour Preference Regression for Offline Reinforcement Learning

reinforcement learning

poster

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.



Scientific discovery serves as the cornerstone for advances in various fields, from the fundamental laws of physics to the intricate mechanisms of biology. 
However, two existing mainstream methods---symbolic regression and dimensional analysis, are significantly limited in this task: the former suffers from low computational efficiency due to the vast search space and often results in formulas without physical meaning; the latter provides a useful theoretical framework but also struggles in searching in a huge space because of lacking effective analysis for the latent variables.
To address this issue, here we propose a framework for efficiently discovering underlying formulas in data, named FIND. We draw inspiration from Buckingham’s Pi theorem, imposing dimensional constraints on the input and output, thereby ensuring discovered expressions possess physical meaning. Additionally, we propose a theoretical scheme for identifying the latent structure as well as a coarse-to-fine framework, significantly reducing the search space of latent variables. This framework not only improves computational efficiency but also enhances model interpretability. From comprehensive experimental validation, FIND showcases its potential to uncover meaningful scientific insights across various domains, providing a robust tool for advancing our understanding of unknown systems.

FIND: A Framework for Discovering Formulas in Data

The reconstruction of low-textured areas is a prominent research focus in multi-view stereo (MVS). In recent years, traditional MVS methods have performed exceptionally well in reconstructing low-textured areas by constructing plane models. However, these methods often encounter issues such as crossing object boundaries and limited perception ranges, which undermine the robustness of plane model construction. Building on previous work (APD-MVS), we propose the DPE-MVS method. By introducing dual-level precision edge information, including fine and coarse edges, we enhance the robustness of plane model construction, thereby improving reconstruction accuracy in low-textured areas. Furthermore, by leveraging edge information, we refine the sampling strategy in conventional PatchMatch MVS and propose an adaptive patch size adjustment approach to optimize matching cost calculation in both stochastic and low-textured areas. This additional use of edge information allows for more precise and robust matching. Our method achieves state-of-the-art performance on the ETH3D and Tanks & Temples benchmarks. Notably, our method outperforms all published methods on the
 ETH3D benchmark.

Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization

Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement without training. However, directly applying them to video restoration and enhancement results in severe temporal flickering artifacts. In this paper, we propose the first framework for zero-shot video restoration and enhancement based on the pre-trained image diffusion model. By replacing the spatial self-attention layer with the proposed SLR temporal attention layer, the pre-trained image diffusion model can take advantage of the temporal correlation between frames. We further propose temporal consistency guidance, spatial-temporal noise sharing, and an early stopping sampling strategy for better temporally consistent sampling. Our method is a plug-and-play module that can be inserted into any diffusion-based zero-shot image restoration or enhancement methods to further improve their performance. Experimental results demonstrate the superiority of our proposed method.

Zero-shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model

Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on leveraging the rich semantic information of pre-trained models (PTMs) in CIL tasks. Prompt learning has been adopted in CIL for its ability to adjust data distribution to better align with pre-trained knowledge. This paper critically examines the limitations of existing methods from the perspective of prompt learning, which heavily rely on input information. To address this issue, we propose a novel PTM-based CIL method called Input-Agnostic  **P**rompt **E**nhancement with Neg**A**tive Feedback **R**egu**L**ation (**PEARL**). In PEARL, we implement an input-agnostic global prompt coupled with an adaptive momentum update strategy to reduce the model's dependency on data distribution, thereby effectively mitigating catastrophic forgetting. Guided by negative feedback regulation, this adaptive momentum update addresses the parameter sensitivity inherent in fixed-weight momentum updates. Furthermore, it fosters the continuous enhancement of the prompt for new tasks by harnessing correlations between different tasks in CIL. Experiments on six benchmarks demonstrate that our method achieves state-of-the-art performance. The code will be made available.

PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning

Graph-based fraud detection is crucial in identifying illegal activities in social networks, finance, and other sectors. Despite recent progress in this area, most of current researches typically require a large amount of annotated data to demonstrate its benefits. In practice, obtaining sufficient high-quality annotated data is challenging, limiting the effectiveness of model training. Therefore, leveraging extremely limited label information is crucial to enhance model performance. We propose a context-aware graph neural network (CGNN) to address this. CGNN performs category semantic decomposition on the contextual neighbor features of the center node to enrich the category semantics. In the neighbor message aggregation stage, the denoising attention mechanism enables the center node to adaptively aggregate heterophilic and homophilic information from neighbors. Particularly for unlabeled data, feature augmentation within the category subspace and consistency regularization driven by entropy minimization ensure that such data can further enhance model performance under explicit semantic guidance. We demonstrate on four real-world datasets that CGNN significantly outperforms other baseline methods with extremely limited labels.

Context-aware Graph Neural Network for Graph-based Fraud Detection with Extremely Limited Labels

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. 
However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but ignore the deformation instability caused by mistaken edge-skipping and visibility occlusion, leading to potential estimation deviation. 
To remedy above issues, we propose DVP-MVS, which innovatively synergizes depth-edge aligned and cross-view priors for robust and visibility-aware patch deformation.
Specifically, to avoid unexpected edge-skipping, we first utilize Depth Anything V2 followed by the Roberts operator to initialize coarse depth and edge maps respectively, both of which are further aligned through an erosion-dilation strategy to generate fine-grained homogeneous boundaries for guiding patch deformation.
In addition, we reform view selection weights as visibility maps and restore visible areas by cross-view depth reprojection, then regard them as cross-view prior to facilitate visibility-aware patch deformation. 
Finally, we improve propagation and refinement with multi-view geometry consistency by introducing aggregated visible hemispherical normals based on view selection and local projection depth differences based on epipolar lines, respectively.
Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization.

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo

Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional memory-based approaches often overfit to limited samples, failing to reinforce old knowledge, with the scarcity of data in few-shot scenarios further exacerbating these issues by hindering effective data augmentation in the latent space. In this paper, we propose a novel retrieval-based solution, starting with a large language model to generate descriptions for each relation. From these descriptions, we introduce a bi-encoder retrieval training paradigm to enrich both sample and class representation learning. Leveraging these enhanced representations, we design a retrieval-based prediction method where each sample "retrieves" the best fitting relation via a reciprocal rank fusion score that integrates both relation description vectors and class prototypes. Extensive experiments on multiple datasets demonstrate that our method significantly advances the state-of-the-art by maintaining robust performance across sequential tasks, effectively addressing catastrophic forgetting.

Few-Shot,  No Problem: Descriptive Continual Relation Extraction

Given an input video of a person and a new garment, the goal of this paper is to synthesize a new video of that person wearing the specified clothing item while maintaining spatio-temporal consistency. Although significant progress has been made in image-based virtual try-on, extending this success to videos often leads to inconsistencies across frames. Several approaches have tried to address temporal consistency in video  virtual try-on, but they encounter major challenges when dealing with long video sequences, including temporal incoherence and high computational costs. To tackle these issues, we reconceptualize video virtual try-on as a conditional video inpainting task, using garments as input conditions. In specific, our approach extends image diffusion models with temporal modules to enhance temporal awareness. To overcome high computational cost on long videos, we introduce ShiftCaching, a training-free technique that ensures temporal coherence while reducing redundant computations. Additionally, we present a new video try-on dataset, the TikTokDress dataset, which includes more complex backgrounds, challenging movements, and higher resolution than existing public datasets. Extensive experiments demonstrate that our approach significantly outperforms existing baselines in both the qualitative and quantitative aspects. Code and dataset will be made available upon paper acceptance.

SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models

Adversarial training is one of the most effective approaches against adversarial attacks.
However, adversarial training has primarily been studied in scenarios where data for all classes is provided, with limited research conducted in the context of incremental learning where knowledge is introduced sequentially.
In this study, we investigate Adversarially Robust Class Incremental Learning (ARCIL), which deals with adversarial robustness in incremental learning.
We first explore a series of baselines that integrate incremental learning with existing adversarial training methods, finding that they lead to conflicts between acquiring new knowledge and retaining past knowledge.
Furthermore, we discover that training new knowledge causes the disappearance of a key characteristic in robust models: a flat loss landscape in input space.
To address such issues, we propose a novel and robust baseline for ARCIL, named \textbf{FL}atness-preserving \textbf{A}dversarial \textbf{I}ncremental learning for \textbf{R}obustness (\textbf{FLAIR}).
Experimental results demonstrate that FLAIR significantly outperforms other baselines.
To the best of our knowledge, we are the first to comprehensively investigate the baselines, challenges, and solutions for ARCIL, which we believe represents a significant advance toward achieving real-world robustness.

Enhancing Robustness in Incremental Learning with Adversarial Training

Solving systems of ordinary differential equations (ODEs) is essential when it comes to understanding the behavior of dynamical systems. Yet, automated solving remains challenging, in particular for nonlinear systems.  Computer algebra systems (CASs) provide support for solving ODEs by first simplifying them, in particular through the use of Lie point symmetries. Finding these symmetries is, however, itself a difficult problem for CASs. Recent works in symbolic regression have shown promising results for recovering symbolic expressions from data. Here, we adapt search-based symbolic regression to the task of finding generators of Lie point symmetries. 
With this approach, we can find symmetries of ODEs that existing CASs cannot find.

Behaviour Preference Regression for Offline Reinforcement Learning

Downloads

Next from AAAI 2025

FIND: A Framework for Discovering Formulas in Data

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Behaviour Preference Regression for Offline Reinforcement Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

FIND: A Framework for Discovering Formulas in Data

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads