Canada

Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets&#39; domains. In this paper, we present a novel offline skill learning framework DuSkill which employs a guided Diffusion model to generate versatile skills extended from the limited skills in datasets, thereby enhancing the robustness of policy learning for tasks in different domains. Specifically, we devise a guided diffusion-based skill decoder in conjunction with the hierarchical encoding to disentangle the skill embedding space into two distinct representations, one for encapsulating domain-invariant behaviors and the other for delineating the factors that induce domain variations in the behaviors. Our DuSkill framework enhances the diversity of skills learned offline, thus enabling to accelerate the learning procedure of high-level policies for different domains.
Through experiments, we show that DuSkill outperforms other skill-based imitation learning and RL algorithms for several long-horizon tasks, demonstrating its benefits in few-shot imitation and online RL.

AAAI 2024

Robust Policy Learning via Offline Skill Diffusion | VIDEO

ml: imitation learning & inverse reinforcement learning

ml: reinforcement learning algorithms

Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets' domains. In this paper, we present a novel offline skill learning framework DuSkill which employs a guided Diffusion model to generate versatile skills extended from the limited skills in datasets, thereby enhancing the robustness of policy learning for tasks in different domains. Specifically, we devise a guided diffusion-based skill decoder in conjunction with the hierarchical encoding to disentangle the skill embedding space into two distinct representations, one for encapsulating domain-invariant behaviors and the other for delineating the factors that induce domain variations in the behaviors. Our DuSkill framework enhances the diversity of skills learned offline, thus enabling to accelerate the learning procedure of high-level policies for different domains.
Through experiments, we show that DuSkill outperforms other skill-based imitation learning and RL algorithms for several long-horizon tasks, demonstrating its benefits in few-shot imitation and online RL.

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. 

Quantitative stock selection is one of the most challenging FinTech tasks due to the non-stationary dynamics and complex market dependencies. Existing studies rely on channel mixing methods, exacerbating the issue of distribution shift in financial time series. Additionally, complex model structures they build make it difficult to handle very long sequences. Furthermore, most of them are based on predefined stock relationships thus making it difficult to capture the dynamic and highly volatile stock markets. To address the above issues, in this paper, we propose Channel-Independent based Spatio-Temporal Hypergraph Pre-trained Attention Networks (CI-STHPAN), a two-stage framework for stock selection, involving Transformer and HGAT based stock time series self-supervised pre-training and stock-ranking based downstream task fine-tuning. We calculate the similarity of stock time series of different channel in dynamic intervals based on Dynamic Time Warping (DTW), and further construct channel-independent stock dynamic hypergraph based on the similarity. Experiments with NASDAQ and NYSE markets data over five years show that our framework outperforms SOTA approaches in terms of investment return ratio (IRR) and Sharpe ratio (SR). Additionally, we find that even without introducing graph information, self-supervised learning based on the vanilla Transformer Encoder also surpasses SOTA results. Notable improvements are gained on the NYSE market. It is mainly attributed to the improvement of fine-tuning approach on Information Coefficient (IC) and Information Ratio based IC (ICIR), indicating that the fine-tuning method enhances the accuracy and stability of the model prediction.

CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph

Current image-text retrieval methods have demonstrated impressive performance in recent years. However, they still face two problems: the inter-modal matching missing problem and the intra-modal semantic loss problem. These problems can significantly affect the accuracy of image-text retrieval. To address these challenges, we propose a novel method called Cross-modal and Uni-modal Soft-label Alignment (CUSA). Our method leverages the power of uni-modal pre-trained models to provide soft-label supervision signals for the image-text retrieval model. Additionally, we introduce two alignment techniques, Cross-modal Soft-label Alignment (CSA) and Uni-modal Soft-label Alignment (USA), to overcome false negatives and enhance similarity recognition between uni-modal samples. Our method is designed to be plug-and-play, meaning it can be easily applied to existing image-text retrieval models without changing their original architectures. Extensive experiments on various image-text retrieval models and datasets, we demonstrate that our method can consistently improve the performance of image-text retrieval and achieve new state-of-the-art results. Furthermore, our method can also boost the uni-modal retrieval performance of image-text retrieval models, enabling it to achieve universal retrieval. The code and supplementary files can be found at https://github.com/lerogo/aaai24_itr_cusa.

Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval

We study a novel approach to information design in the standard traffic model of network congestion games. It captures the natural condition that the demand is unknown to the users of the network. A principal (e.g., a mobility service) commits to a signaling strategy, observes the realized demand and sends a (public) signal to agents (i.e., users of the network). Based on the induced belief about the demand, the users then form an equilibrium. We consider the algorithmic goal of the principal: Compute a signaling scheme that minimizes the expected total cost of the induced equilibrium. We concentrate on single-commodity networks and affine cost functions, for which we obtain the following results.

First, we devise a fully polynomial-time approximation scheme (FPTAS) for the case that the demand can only take two values. It relies on several structural properties of the cost of the induced equilibrium as a function of the updated belief about the distribution of demands. We show that this function is piecewise linear for any number of demands, and monotonic for two demands. 
Second, we give a complete characterization of the graph structures for which it is optimal to fully reveal the information about the realized demand. This signaling scheme turns out to be optimal for all cost functions and probability distributions over demands if and only if the graph is series-parallel. Third, we propose an algorithm that computes the optimal signaling scheme for any number of demands whose time complexity is polynomial in the number of supports that occur in a Wardrop equilibrium for some demand. Finally, we conduct a computational study that tests this algorithm on real-world instances.

Information Design for Congestion Games with Unknown Demand

Many physical systems can be described as a continuous-time dynamical system. In practice, the true system is often unknown and has to be learned from measurement data. Since data is typically collected in discrete time, e.g. by sensors, most methods in Gaussian process (GP) dynamics model learning are trained on one-step ahead predictions. While this scheme is mathematically tempting, it can become problematic in several scenarios, e.g. if measurements are provided at irregularly-sampled time steps or physical system properties have to be conserved. Thus, we aim for a GP model of the true continuous-time dynamics. We tackle this task by leveraging higher-order numerical integrators. These integrators provide the necessary tools to discretize dynamical systems with arbitrary accuracy. However, most higher-order integrators require dynamics evaluations at intermediate time steps, making exact GP inference intractable. In previous work, this problem is often addressed by approximate inference techniques. However, exact GP inference is preferable in many scenarios, e.g. due to its mathematical guarantees. In order to enable direct inference, we propose to leverage multistep and Taylor integrators. We demonstrate how exact inference schemes can be derived for these types of integrators. Further, we derive tailored sampling schemes that allow one to draw consistent dynamics functions from the posterior. The learned model can thus be integrated with arbitrary integrators, just like a standard dynamical system. We show empirically and theoretically that our approach yields an accurate representation of the continuous-time system.

Exact Inference for Continuous-Time Gaussian Process Dynamics | VIDEO

Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies. However, such universal basis functions can limit the representation capability in local regions where a specific component is unnecessary, resulting in unpleasant artifacts. To this end, we introduce a learnable spatial mask that effectively dispatches distinct Fourier bases into respective regions. This translates into collaging Fourier patches, thus enabling an accurate representation of complex signals. Comprehensive experiments demonstrate the superior reconstruction quality of the proposed approach over existing baselines across various INR tasks, including image fitting, video representation, and 3D shape representation. Our method outperforms all other baselines, improving the image fitting PSNR by over 3dB and 3D reconstruction to 98.81 IoU and 0.0011 Chamfer Distance.

Learning Spatially Collaged Fourier Bases for Implicit Neural Representation

Preference-based Reinforcement Learning (PbRL) enables non-experts to train Reinforcement Learning models using preference feedback. However, the effort required to collect preference labels from real humans means that PbRL research primarily relies on synthetic labellers. We validate the most common synthetic labelling strategy by comparing against labels collected from a crowd of humans on three Deep Mind Control (DMC) suite tasks: stand, walk, and run. We find that: (1) the synthetic labels are a good proxy for real humans under some circumstances, (2) strong preference label agreement between human and synthetic labels is not necessary for similar policy performance, (3) policy performance is higher at the start of training from human feedback and is higher at the end of training from synthetic feedback, and (4) training on only examples with high levels of inter-annotator agreement does not meaningfully improve policy performance. Our results justify the use of synthetic labellers to develop and ablate PbRL methods, and provide insight into how human labelling changes over the course of policy training.

Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated

Learning to forecast bimanual object manipulation sequences from unimanual observations has broad applications in assistive robots and augmented reality. This challenging task requires us to first infer motion from the missing arm and the object it would have been manipulating were the person bimanual, then forecast the human and object motion while maintaining hand-object contact during manipulation. Previous attempts model the hand-object interactions only implicitly, and thus tend to produce unrealistic motion where the objects float in air. We address this with a novel neural network that (i) identifies and forecasts the pose for only the objects undergoing motion through an object motion module and (ii) refines human pose predictions by encouraging hand-object contact during manipulation through an ensemble of human pose predictors. The components are also designed to be generic enough for use in both unimanual and bimanual contexts. Our approach outperforms the state-of-the-art pose forecasting methods on bimanual manipulation datasets.

Forecasting Bimanual Object Manipulation Sequences from Unimanual Observations

Explaining the decision process of machine learning algorithms is nowadays crucial for both model’s performance enhancement and human comprehension. This can be achieved by assessing the variable importance of single variables, even for high-capacity non-linear methods, e.g. Deep Neural Networks (DNNs). While only removal-based approaches, such as Permutation Importance (PI), can bring statistical validity, they return misleading results when variables are correlated. Conditional Permutation Importance (CPI) bypasses PI’s limitations in such cases. However, in high-dimensional settings, where high correlations between the variables cancel their conditional importance, the use of CPI as well as other methods leads to unreliable results, besides prohibitive computation costs. Grouping variables statistically via clustering or some prior knowledge gains some power back and leads to better interpretations. In this work, we introduce BCPI (Block-Based Conditional Permutation Importance), a new generic framework for variable importance computation with statistical guarantees handling both single and group cases. Furthermore, as handling groups with high cardinality (such as a set of observations of a given modality) are both time-consuming and resource-intensive, we also introduce a new stacking approach extending the DNN architecture with sub-linear layers adapted to the group structure. We show that the ensuing approach extended with stacking controls the type-I error even with highly-correlated groups and shows top accuracy across benchmarks. Furthermore, we perform a real-world data analysis in a large-scale medical dataset where we aim to show the consistency between our results and the literature for a biomarker prediction.

Variable Importance in High-Dimensional Settings Requires Grouping

In light of the advances in big data, high-dimensional datasets are often encountered. Incorporating them into data-driven models can enhance performance; however, this comes at the cost of high computation and the risk of overfitting, particularly due to abundant redundant features. Identifying an informative subset of the features helps in reducing the dimensionality and enhancing model interpretability. In this paper, we propose a novel framework for unsupervised feature selection, called Selective Deep Auto-Encoder (SDAE). It aims to reduce the number of features used in unlabeled datasets without compromising the quality of information obtained. It achieves this by selecting sufficient features - from the original feature set - capable of representing the entire feature space and reconstructing them. Architecturally, it leverages the use of highly nonlinear latent representations in deep Autoencoders and intrinsically learns, in an unsupervised fashion, the relevant and globally representative subset of features through a customized Selective Layer. Extensive experimental results on three high-dimensional public datasets have shown promising feature selection performance by SDAE in comparison to other existing state-of-the-art unsupervised feature selection methods.

Selective Deep Autoencoder for Unsupervised Feature Selection

Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might limit their adaptability to an increasing set of anomaly detection tasks due to the priors in the selection of auxiliary datasets or the strategy of anomaly simulation. To tackle this challenge, we first introduce a prior-less anomaly generation paradigm and subsequently develop an innovative unsupervised anomaly detection framework named GRAD, grounded in this paradigm. GRAD comprises three essential components: (1) a diffusion model (PatchDiff) to generate contrastive patterns by preserving the local structures while disregarding the global structures present in normal images, (2) a self-supervised reweighting mechanism to handle the challenge of long-tailed and unlabeled contrastive patterns generated by PatchDiff, and (3) a lightweight patch-level detector to efficiently distinguish the normal patterns and reweighted contrastive patterns. The generation results of PatchDiff effectively expose various types of anomaly patterns, e.g. structural and logical anomaly patterns. In addition, extensive experiments on both MVTec AD and MVTec LOCO datasets also support the aforementioned observation and demonstrate that GRAD achieves competitive anomaly detection accuracy and superior inference speed.

Robust Policy Learning via Offline Skill Diffusion | VIDEO

Downloads

Next from AAAI 2024

CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Robust Policy Learning via Offline Skill Diffusion | VIDEO

.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 2024

CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads