Offline reinforcement learning (RL) offers an appealing approach to real-world tasks by learning policies from pre-collected datasets without interacting with the environment. However, the performance of existing offline RL algorithms heavily depends on the scale and state-action space coverage of datasets. Real-world data collection is often expensive and uncontrollable, leading to small and narrowly covered datasets and posing significant challenges for practical deployments of offline RL. In this paper, we provide a new insight that leveraging the fundamental symmetry of system dynamics can substantially enhance offline RL performance under small datasets. Specifically, we propose a Time-reversal symmetry (T-symmetry) enforced Dynamics Model (TDM), which establishes consistency between a pair of forward and reverse latent dynamics. TDM provides both well-behaved representations for small datasets and a new reliability measure for OOD samples based on compliance with the T-symmetry. These can be readily used to construct a new offline RL algorithm (TSRL) with less conservative policy constraints and a reliable latent space data augmentation procedure. Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability.
Rain-by-snow weather removal is a specialized task in weather-degraded image restoration aiming to eliminate coexisting rain streaks and snow particles. In this paper, we propose RSFormer, an efficient and effective Transformer that addresses this challenge. Initially, we explore the proximity of convolution networks (ConvNets) and vision Transformers (ViTs) in hierarchical architectures and experimentally find they perform approximately at intra-stage feature learning. On this basis, we utilize a Transformer-like convolution block (TCB) that replaces the computationally expensive self-attention while preserving attention characteristics for adapting to input content. We also demonstrate that cross-stage progression is critical for performance improvement, and propose a global-local self-attention sampling mechanism (GLASM) that down-/up-samples features while capturing both global and local dependencies. Finally, we synthesize two novel rain-by-snow datasets, RSCityScape and RS100K, to evaluate our proposed RSFormer. Extensive experiments verify that RSFormer achieves the best trade-off between performance and time-consumption compared to other restoration methods. For instance, it outperforms Restormer with a 1.53% reduction in the number of parameters and a 15.6% reduction in inference time. Datasets, source code and pre-trained models are available at \url{https://github.com/chdwyb/RSFormer}.
One of the key challenges in deploying RL to real-world applications is to adapt to variations of unknown environment contexts, such as changing terrains in robotic tasks and fluctuated bandwidth in congestion control. Existing works on adaptation to unknown environment contexts either assume the contexts are the same for the whole episode or assume the context variables are Markovian. However, in many real-world applications, the environment context usually stays stable for a stochastic period and then changes in an abrupt and unpredictable manner within an episode, resulting in a segment structure, which existing works fail to address. To leverage the segment structure of piecewise stable context in real-world applications, in this paper, we propose a \textit{\textbf{Se}gmented \textbf{C}ontext \textbf{B}elief \textbf{A}ugmented \textbf{D}eep~(SeCBAD)} RL method. Our method can jointly infer the belief distribution over latent context with the posterior over segment length and perform more accurate belief context inference with observed data within the current context segment. The inferred belief context can be leveraged to augment the state, leading to a policy that can adapt to abrupt variations in context. We demonstrate empirically that SeCBAD can infer context segment length accurately and outperform existing methods on a toy grid world environment and Mujuco tasks with piecewise-stable context.
Federated learning is a distributed learning that allows each client to keep the original data locally and only upload the parameters of the local model to the server. Despite federated learning can address data island, it remains challenging to train with data heterogeneous in a real application. In this paper, we propose FedSiam-DA, a novel dual-aggregated contrastive federated learning approach, to personalize both local and global models, under various settings of data heterogeneity. Firstly, based on the idea of contrastive learning in the siamese network, FedSiam-DA regards the local and global model as different branches of the siamese network during the local training and controls the update direction of the model by constantly changing model similarity to personalize the local model. Secondly, FedSiam-DA introduces dynamic weights based on model similarity for each local model and exercises the dual-aggregated mechanism to further improve the generalization of the global model. Moreover, we provide extensive experiments on benchmark datasets, the results demonstrate that FedSiam-DA achieves outperforming several previous FL approaches on heterogeneous datasets.
Weighted Majority Voting (WMV) is a well-known optimal decision rule for collective decision making, given the probability of sources to provide accurate information (trustworthiness). However, in reality, the trustworthiness is not a known quantity to the decision maker - they have to rely on an estimate called trust. A (machine learning) algorithm that computes trust is called unbiased when it has the property that it does not systematically overestimate or underestimate the trustworthiness. To formally analyse the uncertainty to the decision process, we introduce and analyse two important properties of such unbiased trust values: stability of correctness and stability of optimality. Stability of correctness means that the decision accuracy that the decision maker believes they achieved is equal to the actual accuracy. We prove stability of correctness holds. Stability of optimality means that the decisions made based on trust, are equally good as they would have been if they were based on trustworthiness. Stability of optimality does not hold. We analyse the difference between the two, and bounds thereon. We also present an overview of how sensitive decision correctness is to changes in trust and trustworthiness.
Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data due to covariate shift. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations. DMIL adopts a novel cooperative-yet-adversarial learning strategy, which uses the discriminator to guide and couple the learning process of the policy and dynamics model, resulting in improved model performance and robustness. Our framework can also be extended to the case when demonstrations contain a large proportion of suboptimal data. Experimental results show that DMIL and its extension achieve superior performance and robustness compared to state-of-the-art offline IL methods under small datasets.
In recent years, Mixture-of-Experts (MoE) has emerged as a promising technique for deep learning that can scale the model capacity to trillion-plus parameters while reducing the computing cost via sparse computation. While MoE opens a new frontier of exceedingly large models, its implementation over thousands of GPUs has been limited due to mismatch between the dynamic nature of MoE and static parallelism/pipelining of the system. We present Tutel, a highly scalable stack design and implementation for MoE with dynamically adaptive parallelism and pipelining. Tutel delivers adaptive parallelism switching and adaptive pipelining at runtime, which achieves up to 1.74x and 2.00x single MoE layer speedup, respectively. We also propose a novel two-dimensional hierarchical algorithm for MoE communication speedup that outperforms the previous state-of-the-art up to 20.7x over 2,048 GPUs. Aggregating all techniques, Tutel finally delivers 4.96x and 5.75x speedup of a single MoE layer on 16 GPUs and 2,048 GPUs, respectively, over Fairseq: Meta's Facebook AI Research Sequence-to-Sequence Toolkit (Tutel is now partially adopted by Fairseq). Tutel source code is available in public: https://github.com/microsoft/tutel . Our evaluation shows that Tutel efficiently and effectively runs a real-world MoE-based model named SwinV2-MoE, built upon Swin Transformer V2, a state-of-the-art computer vision architecture. On efficiency, Tutel accelerates SwinV2-MoE, achieving up to 1.55x and 2.11x speedup in training and inference over Fairseq, respectively. On effectiveness, the SwinV2-MoE model achieves superior accuracy in both pre-training and down-stream computer vision tasks such as COCO object detection than the counterpart dense model, indicating the readiness of Tutel for end-to-end real-world model training and inference. SwinV2-MoE is open sourced in https://github.com/microsoft/Swin-Transformer .
Federated learning (FL) is a collaborative learning paradigm where participants jointly train a powerful model without sharing their private data. One desirable property for FL is the implementation of the right to be forgotten (RTBF), i.e., a leaving participant has the right to request to delete its private data from the global model. However, unlearning itself may not be enough to implement RTBF unless the unlearning effect can be independently verified, an important aspect that has been overlooked in the current literature. In this paper, we prompt the concept of verifiable federated unlearning, and propose VeriFi, a unified framework integrating federated unlearning and verification that allows systematic analysis of the unlearning and quantification of its effect, with different combinations of multiple unlearning and verification methods. In VeriFi, the leaving participant is granted the right to verify (RTV), that is, the participant notifies the server before leaving, then actively verifies the unlearning effect in the next few communication rounds. The unlearning is done at the server side immediately after receiving the leaving notification, while the verification is done locally by the leaving participant via two steps: marking (injecting carefully-designed markers to fingerprint the leaver) and checking (examining the change of the global model's performance on the markers). Based on VeriFi, we conduct the first systematic and large-scale study for verifiable federated unlearning, considering 7 unlearning methods and 5 verification methods. Particularly, we propose a more efficient and FL-friendly unlearning method, and two more effective and robust non-invasive-verification methods. We extensively evaluate VeriFi on 7 datasets and 4 types of deep learning models. Our analysis establishes important empirical understandings for more trustworthy federated unlearning.
This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network. The aircraft recognizability analysis shows that: (1) the semantic feature of an aircraft is motion patterns driven by the kinetic characteristics, and (2) the grammatical features contained in the radar cross-section (RCS) signals present spatial-temporal-frequency (STF) diversity decided by both the electromagnetic radiation shape and motion pattern of the aircraft. Then a STF graph attention convolutional network (STFGACN) is developed to distill semantic features from the RCS signals received by the heterogeneous radar network. Extensive experiment results verify that the STFGACN outperforms the baseline methods in terms of detection accuracy, and ablation experiments are carried out to further show that the expansion of the information dimension can gain considerable benefits to perform robustly in the low signal-to-noise ratio region.
With the development of traffic prediction technology, spatiotemporal prediction models have attracted more and more attention from academia communities and industry. However, most existing researches focus on reducing model's prediction error but ignore the error caused by the uneven distribution of spatial events within a region. In this paper, we study a region partitioning problem, namely optimal grid size selection problem (OGSS), which aims to minimize the real error of spatiotemporal prediction models by selecting the optimal grid size. In order to solve OGSS, we analyze the upper bound of real error of spatiotemporal prediction models and minimize the real error by minimizing its upper bound. Through in-depth analysis, we find that the upper bound of real error will decrease then increase when the number of model grids increase from 1 to the maximum allowed value. Then, we propose two algorithms, namely Ternary Search and Iterative Method, to automatically find the optimal grid size. Finally, the experiments verify that the error of prediction has the same trend as its upper bound, and the change trend of the upper bound of real error with respect to the increase of the number of model grids will decrease then increase. Meanwhile, in a case study, by selecting the optimal grid size, the order dispatching results of a state-of-the-art prediction-based algorithm can be improved up to 13.6%, which shows the effectiveness of our methods on tuning the region partition for spatiotemporal prediction models.