On Evolving Attention Towards Domain Adaptation

Towards better unsupervised domain adaptation (UDA). Recently, researchers propose various domain-conditioned attention modules and make promising progresses. However, considering that the configuration of attention, i.e., the type and the position of attention module, affects the performance significantly, it is more generalized to optimize the attention configuration automatically to be specialized for arbitrary UDA scenario. For the first time, this paper proposes EvoADA: a novel framework to evolve the attention configuration for a given UDA task without human intervention. In particular, we propose a novel search space containing diverse attention configurations. Then, to evaluate the attention configurations and make search procedure UDA-oriented (transferability + discrimination), we apply a simple and effective evaluation strategy: 1) training the network weights on two domains with off-the-shelf domain adaptation methods; 2) evolving the attention configurations under the guide of the discriminative ability on the target domain. Experiments on various kinds of cross-domain benchmarks, i.e., Office-31, Office-Home, CUB-Paintings, and Duke-Market-1510, reveal that the proposed EvoADA consistently boosts multiple state-of-the-art domain adaptation approaches, and the optimal attention configurations help them achieve better performance.

An Improved Two-Archive Evolutionary Algorithm for Constrained Multi-Objective Optimization

Constrained multi-objective optimization problems (CMOPs) are ubiquitous in real-world engineering optimization scenarios. A key issue in constrained multi-objective optimization is to strike a balance among convergence, diversity and feasibility. A recently proposed two-archive evolutionary algorithm for constrained multi-objective optimization (C-TAEA) has be shown as a latest algorithm. However, due to its simple implementation of the collaboration mechanism between its two co-evolving archives, C-TAEA is struggling when solving problems whose \textit{pseudo} Pareto-optimal front, which does not take constraints into consideration, dominates the \textit{feasible} Pareto-optimal front. In this paper, we propose an improved version C-TAEA, dubbed C-TAEA-II, featuring an improved update mechanism of two co-evolving archives and an adaptive mating selection mechanism to promote a better collaboration between co-evolving archives. Empirical results demonstrate the competitiveness of the proposed C-TAEA-II in comparison with five representative constrained evolutionary multi-objective optimization algorithms.

Multi-Objective Reinforcement Learning based Multi-Microgrid System Optimisation Problem

Microgrids with energy storage systems and distributed renewable energy sources play a crucial role in reducing the consumption from traditional power sources and the emission of $CO_2$. Connecting multi microgrid to a distribution power grid can facilitate a more robust and reliable operation to increase the security and privacy of the system. The proposed model consists of three layers, smart grid layer, independent system operator (ISO) layer and power grid layer. Each layer aims to maximise its benefit. To achieve these objectives, an intelligent multi-microgrid energy management method is proposed based on the multi-objective reinforcement learning (MORL) techniques, leading to a Pareto optimal set. A non-dominated solution is selected to implement a fair design in order not to favour any particular participant. The simulation results demonstrate the performance of the MORL and verify the viability of the proposed approach.

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition. First, lattices from first-pass decoding are expanded by the proposed posterior-based lattice expansion algorithm. Second, each expanded lattice is converted into a minimal list of hypotheses that covers every arc. Each hypothesis is constrained to be the best path for at least one arc it includes. For each lattice, the neural LM scores of the minimal list are computed in parallel and are then integrated back to the lattice in the rescoring stage. Experiments on the Switchboard dataset show that the proposed rescoring strategy obtains comparable recognition performance and generates more compact lattices than a competitive baseline method. Furthermore, the parallel rescoring method offers more flexibility by simplifying the integration of PyTorch-trained neural LMs for lattice rescoring with Kaldi.

Combinatorial Bandits under Strategic Manipulations

We study the problem of combinatorial multi-armed bandits (CMAB) under strategic manipulations of rewards, where each arm can modify the emitted reward signals for its own interest. Our setting elaborates a more realistic model of adaptive arms that imposes relaxed assumptions compared to adversarial corruptions and adversarial attacks. Algorithms designed under strategic arms gain robustness in real applications while avoiding being overcautious and hampering the performance. We bridge the gap between strategic manipulations and adversarial attacks by investigating the optimal colluding strategy among arms under the MAB problem. We then propose a strategic variant of the combinatorial UCB algorithm, which has a regret of at most $O(m\log T + m B_{max})$ under strategic manipulations, where $T$ is the time horizon, $m$ is the number of arms, and $B_{max}$ is the maximum budget. We further provide lower bounds on the strategic budgets for attackers to incur certain regret of the bandit algorithm. Extensive experiments corroborate our theoretical findings on robustness and regret bounds, in a variety of regimes of manipulation budgets.

On The Consistency Training for Open-Set Semi-Supervised Learning

Conventional semi-supervised learning (SSL) methods, e.g., MixMatch, achieve great performance when both labeled and unlabeled dataset are drawn from the same distribution. However, these methods often suffer severe performance degradation in a more realistic setting, where unlabeled dataset contains out-of-distribution (OOD) samples. Recent approaches mitigate the negative influence of OOD samples by filtering them out from the unlabeled data. Our studies show that it is not necessary to get rid of OOD samples during training. On the contrary, the network can benefit from them if OOD samples are properly utilized. We thoroughly study how OOD samples affect DNN training in both low- and high-dimensional spaces, where two fundamental SSL methods are considered: Pseudo Labeling (PL) and Data Augmentation based Consistency Training (DACT). Conclusion is twofold: (1) unlike PL that suffers performance degradation, DACT brings improvement to model performance; (2) the improvement is closely related to class-wise distribution gap between the labeled and the unlabeled dataset. Motivated by this observation, we further improve the model performance by bridging the gap between the labeled and the unlabeled datasets (containing OOD samples). Compared to previous algorithms paying much attention to distinguishing between ID and OOD samples, our method makes better use of OOD samples and achieves state-of-the-art results.

Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets

This work studies Hyperspectral image (HSI) super-resolution (SR). HSI SR is characterized by high-dimensional data and a limited amount of training examples. This exacerbates the undesirable behaviors of neural networks such as memorization and sensitivity to out-of-distribution samples. This work addresses these issues with three contributions. First, we propose a simple, yet effective data augmentation routine, termed Spectral Mixup, to construct effective virtual training samples. Second, we observe that HSI SR and RGB image SR are correlated and develop a novel multi-tasking network to train them jointly so that the auxiliary task RGB image SR can provide additional supervision. Finally, we extend the network to a semi-supervised setting so that it can learn from datasets containing low-resolution HSIs only. With these contributions, our method is able to learn from heterogeneous datasets and lift the requirement for having a large amount of HD HSI training samples. Extensive experiments on four datasets show that our method outperforms existing methods significantly and underpin the relevance of our contributions. The code of this work will be released soon.

One for More: Selecting Generalizable Samples for Generalizable ReID Model

Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch. It will inevitably cause the model to over-fit the data in the dominant position (e.g., head data in imbalanced class, easy samples or noisy samples). %We call the sample that updates the model towards generalizing on more data a generalizable sample. The latest resampling methods address the issue by designing specific criterion to select specific samples that trains the model generalize more on certain type of data (e.g., hard samples, tail data), which is not adaptive to the inconsistent real world ReID data distributions. Therefore, instead of simply presuming on what samples are generalizable, this paper proposes a one-for-more training objective that directly takes the generalization ability of selected samples as a loss function and learn a sampler to automatically select generalizable samples. More importantly, our proposed one-for-more based sampler can be seamlessly integrated into the ReID training framework which is able to simultaneously train ReID models and the sampler in an end-to-end fashion. The experimental results show that our method can effectively improve the ReID model training and boost the performance of ReID models.

Better Knowledge Retention through Metric Learning

In continual learning, new categories may be introduced over time, and an ideal learning system should perform well on both the original categories and the new categories. While deep neural nets have achieved resounding success in the classical supervised setting, they are known to forget about knowledge acquired in prior episodes of learning if the examples encountered in the current episode of learning are drastically different from those encountered in prior episodes. In this paper, we propose a new method that can both leverage the expressive power of deep neural nets and is resilient to forgetting when new categories are introduced. We found the proposed method can reduce forgetting by 2.3x to 6.9x on CIFAR-10 compared to existing methods and by 1.8x to 2.7x on ImageNet compared to an oracle baseline.

DeRF: Decomposed Radiance Fields

With the advent of Neural Radiance Fields (NeRF), neural networks can now render novel views of a 3D scene with quality that fools the human eye. Yet, generating these images is very computationally intensive, limiting their applicability in practical scenarios. In this paper, we propose a technique based on spatial decomposition capable of mitigating this issue. Our key observation is that there are diminishing returns in employing larger (deeper and/or wider) networks. Hence, we propose to spatially decompose a scene and dedicate smaller networks for each decomposed part. When working together, these networks can render the whole scene. This allows us near-constant inference time regardless of the number of decomposed parts. Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering. Our experiments show that for real-world scenes, our method provides up to 3x more efficient inference than NeRF (with the same rendering quality), or an improvement of up to 1.0~dB in PSNR (for the same inference cost).