United States

Heating and cooling systems in buildings account for 31% of global energy use, much of which are regulated by Rule Based Controllers (RBCs) that neither maximise energy efficiency nor minimise emissions by interacting optimally with the grid. Control via Reinforcement Learning (RL) has been shown to significantly improve building energy efficiency, but existing solutions require access to building-specific simulators or data that cannot be expected for every building in the world. In response, we show it is possible to obtain emission-reducing policies without such knowledge a priori–a paradigm we call zero-shot building control. We combine ideas from system identification and model-based RL to create PEARL (Probabilistic Emission-Abating Reinforcement Learning) and show that a short period of active exploration is all that is required to build a performant model. In experiments across three varied building energy simulations, we show PEARL outperforms an existing RBC once, and popular RL baselines in all cases, reducing building emissions by as much as 31% whilst maintaining thermal comfort. Our source code is available online via: https://enjeeneer.io/projects/pearl/.

AAAI 2023

Low Emission Building Control with Zero-Shot Reinforcement Learning

environment & sustainability

app: energy

ml: reinforcement learning algorithms

ml: applications

ml: lifelong and continual learning

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/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.

poster

Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under ideal experimental settings. Generally, these classic deep learning methods are built on the \emph{i.i.d.} assumption, supposing the training and test data are drawn from the same distribution independently and identically. However, the aforementioned \emph{i.i.d.} assumption is, in general, unavailable in the real-world scenarios, and as a result, leads to sharp performance decay of deep learning algorithms. Behind this, domain shift is one of the primary factors to be blamed. In order to tackle this problem, we propose using \textbf{Po}tential \textbf{E}nergy \textbf{R}anking (PoER) to decouple the object feature and the domain feature in given images, promoting the learning of label-discriminative representations while filtering out the irrelevant correlations between the objects and the background. PoER employs the ranking loss in shallow layers to make features with identical category and domain labels close to each other and vice versa. This makes the neural networks aware of both objects and background characteristics, which is vital for generating domain-invariant features. Subsequently, with the stacked convolutional blocks, PoER further uses the contrastive loss to make features within the same categories distribute densely no matter domains, filtering out the domain information progressively for feature alignment. PoER reports superior performance on domain generalization benchmarks, improving the average top-1 accuracy by at least 1.20\% compared to the existing methods. Moreover, we use PoER in the ECCV 2022 NICO Challenge, achieving top place with only a vanilla ResNet-18 and winning the \emph{jury award}. The code has been made publicly available at: \texttt{https://github.com/ForeverPs/PoER}.

Domain Decorrelation with Potential Energy Ranking

Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In this paper, we investigate the robustness of existing (demographic) fairness criteria when the algorithm is trained on biased data. We consider two forms of dataset bias: errors by prior decision makers in the labeling process, and errors in the measurement of the features of disadvantaged individuals. We analytically show that some constraints (such as Demographic Parity) can remain robust when facing certain statistical biases, while others (such as Equalized Odds) are significantly violated if trained on biased data. We provide numerical experiments based on three real-world datasets (the FICO, Adult, and German credit score datasets) supporting our analytical findings. While fairness criteria are primarily chosen under normative considerations in practice, our results show that naively applying a fairness constraint can lead to not only a loss in utility for the decision maker, but more severe unfairness when data bias exists. Thus, understanding how fairness criteria react to different forms of data bias presents a critical guideline for choosing among existing fairness criteria, or for proposing new criteria, when available datasets may be biased.

Social Bias Meets Data Bias: The Impacts of Labeling and Measurement Errors on Fairness Criteria

Denoising Diffusion Probabilistic Models (DDPMs) have shown a powerful capacity to model various data distributions. We find that most existing conditional DDPMs only relate conditions to the reverse process to fit unconditional forward process, which to some extent limits their learning capacity. In this work, we propose a novel and flexible conditional diffusion model by introducing conditions into the forward process. Specifically, we allocate an exclusive forward diffusion trajectory for each condition according to some shifting rules, which can improve the utilization rate of latent space and make the training of corresponding reverse process break free from condition modeling. In this way, the modified diffusion model can achieve better training efficiency and sampling performance than the vanilla one. We formulate our method, which we call \textbf{ShiftDDPMs}, and provide a unified point of view on existing related methods. Extensive qualitative and quantitative experiments on image synthesis demonstrate the advantages of our method.

ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories

Fairness and privacy are two important concerns in social decision-making processes such as resource allocation. We study privacy in the fair allocation of indivisible resources using the well-established framework of differential privacy. We present algorithms for approximate envy-freeness and proportionality when two instances are considered to be adjacent if they differ only on the utility of a single agent for a single item. On the other hand, we provide strong negative results for both fairness criteria when the adjacency notion allows the entire utility function of a single agent to change.

Differentially Private Fair Division

We propose a robust and accurate non-parametric method for single-view 3D face reconstruction (SVFR). While tremendous efforts have been devoted to parametric SVFR, a visible gap still lies between the result 3D shape and the ground truth. We believe there are two major obstacles: 1) the representation of the parametric model is limited to a certain face database; 2) 2D images and 3D shapes in the fitted datasets are distinctly misaligned. To resolve these issues, a large-scale pseudo 2D&3D dataset is created by first rendering the detailed 3D faces, then swapping the face in the wild images with the rendered face. These pseudo 2D&3D pairs are created from publicly available datasets which eliminate the gaps between 2D and 3D data while covering diverse appearances, poses, scenes, and illumination. We further propose a non-parametric scheme to learn a well-generalized SVFR model from the created dataset, and the proposed hierarchical signed distance function turns out to be effective in predicting middle-scale and small-scale 3D facial geometry. Our model outperforms previous methods on FaceScape-wild/lab and MICC benchmarks and is well generalized to various appearances, poses, expressions, and in-the-wild environments. The code is released at https://github.com/zhuhao-nju/rafare.

RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from pseudo 2D&3D pairs

Graph-based methods have hitherto been used to pursue the coherent patterns of data due to its ease of implementation and efficiency. These methods have been increasingly applied in multi-view learning and achieved promising performance in various clustering tasks. However, despite their noticeable empirical success, existing graph-based multi-view clustering methods may still suffer the suboptimal solution considering that multi-view data can be very complicated in raw feature space. Moreover, existing methods usually adopt the similarity metric by an ad hoc approach, which largely simplifies the relationship among real-world data and results in an inaccurate output. To address these issues, we propose to seamlessly integrates metric learning and graph learning for multi-view clustering. Specifically, we employ a useful metric to depict the inherent structure with linearity-aware of affinity graph representation learned based on the self-expressiveness property. Furthermore, instead of directly utilizing the raw features, we prefer to recover a smooth representation such that the geometric structure of the original data can be retained. We model the above concerns into a unified learning framework, and hence complements each learning subtask in a mutual reinforcement manner. The empirical studies corroborate our theoretical findings, and demonstrate that the proposed method is able to boost the multi-view clustering performance.

Metric Multi-view Graph Clustering

Online optimization with multiple budget constraints is challenging since the online decisions over a short time horizon are coupled together by strict inventory constraints. The existing manually-designed algorithms cannot achieve satisfactory
average performance for this setting because they often need a large number of time steps for convergence and/or may violate the inventory constraints. In this paper, we propose a new machine learning (ML) assisted unrolling approach, called LAAU (Learning-Assisted Algorithm Unrolling), which unrolls the agent’s online decision pipeline and leverages an ML model for updating the Lagrangian multiplier online. For efficient training via backpropagation, we derive gradients of the decision pipeline over time. We also provide the average cost bounds for two cases when training data is available offline and collected online, respectively. Finally, we present numerical results to highlight that LAAU can outperform the existing baselines.

Learning-Assisted Algorithm Unrolling for Online Optimization with Budget Constraints

Enhancing model prediction confidence on unlabeled target data is an important objective in Unsupervised Domain Adaptation (UDA). In this paper, we explore adversarial training on penultimate activations, i.e., input features of the final linear classification layer. We show that this strategy is more efficient and better correlated with the objective of boosting prediction confidence than adversarial training on input images or intermediate features, as used in previous works. Furthermore, with activation normalization  commonly used in domain adaptation to reduce domain gap, we derive two variants and systematically analyze the effects of normalization on our adversarial training. This is illustrated both in theory and through empirical analysis on real adaptation tasks. Extensive experiments are conducted on popular UDA benchmarks under both standard setting and source-data free setting. The results validate that our method achieves the best scores against previous arts.

Domain Adaptation with Adversarial Training on Penultimate Activations

The vulnerability of deep neural network models to adversarial example attacks is a practical challenge in many artificial intelligence applications. A recent line of work shows that the use of randomization in adversarial training is the key to find optimal strategies against adversarial example attacks. However, in a fully randomized setting where both the defender and the attacker can use randomized strategies, there are no efficient algorithm for finding such an optimal strategy. To fill the gap, we propose the first algorithm of its kind, called FRAT, which models the problem with a new infinite-dimensional continuous-time flow on probability distribution spaces. FRAT maintains a lightweight mixture of models for the defender, with flexibility to efficiently update mixing weights and model parameters at each iteration. Furthermore, FRAT utilizes lightweight sampling subroutines to construct a random strategy for the attacker. We prove that the continuous-time limit of FRAT converges to a mixed Nash equilibria in a zero-sum game formed by a defender and an attacker. Experimental results also demonstrate the efficiency of FRAT on CIFAR-10 and CIFAR-100 datasets.

Premium content

Low Emission Building Control with Zero-Shot Reinforcement Learning

Downloads

Next from AAAI 2023

Domain Decorrelation with Potential Energy Ranking

Similar lecture

PowRL: A Reinforcement Learning Framework for Robust Management of Power Networks