Search

A critical milestone for the advancement of nanoscale organic circuitry is the fabrication of well-defined conjugated polymers on non-metal substrates. Here, the authors demonstrate extended polycyclic aromatic chains from repetitive cycloadditions which form not only on metals, but also on boron nitride layers and in the solid state.

Polyaromatic hydrocarbons can be precisely manipulated to yield ever more complex and discrete graphene analogs, such as nanographenes. Here, the authors use azomethine ylide homocoupling to insert an antiaromatic pyrazine ring into the core of a nanographene, and characterize the molecule’s unique electronic character.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

We have examined the geometric and electronic structures of iron phthalocyanine assemblies on a Cu(111) surface at different sub- to mono-layer coverages and the changes induced by thermal annealing at temperatures between 250 and 320 °C by scanning tunneling microscopy, x-ray photoelectron spectroscopy, and x-ray absorption spectroscopy. The symmetry breaking observed in scanning tunneling microscopy images is found to be coverage dependent and to persist upon annealing. Further, we find that annealing to temperatures between 300 and 320 °C leads to both desorption of iron phthalocyanine molecules from the surface and their agglomeration. We see clear evidence of temperature-induced homocoupling reactions of the iron phthalocyanine molecules following dehydrogenation of their isoindole rings, similar to what has been observed for related tetrapyrroles on transition metal surfaces. Finally, spectroscopy indicates a modified substrate-adsorbate interaction upon annealing with a shortened bond distance. This finding could potentially explain a changed reactivity of Cu-supported iron phthalocyanine in comparison to that of the pristine compound. [ABSTRACT FROM AUTHOR]

Conventionally, federated learning aims to optimize a single objective, typically the utility. However, for a federated learning system to be trustworthy, it needs to simultaneously satisfy multiple objectives, such as maximizing model performance, minimizing privacy leakage and training costs, and being robust to malicious attacks. Multi-Objective Optimization (MOO) aiming to optimize multiple conflicting objectives simultaneously is quite suitable for solving the optimization problem of Trustworthy Federated Learning (TFL). In this article, we unify MOO and TFL by formulating the problem of constrained multi-objective federated learning (CMOFL). Under this formulation, existing MOO algorithms can be adapted to TFL straightforwardly. Different from existing CMOFL algorithms focusing on utility, efficiency, fairness, and robustness, we consider optimizing privacy leakage along with utility loss and training cost, the three primary objectives of a TFL system. We develop two improved CMOFL algorithms based on NSGA-II and PSL, respectively, to effectively and efficiently find Pareto optimal solutions and provide theoretical analysis on their convergence. We design quantitative measurements of privacy leakage, utility loss, and training cost for three privacy protection mechanisms: Randomization, BatchCrypt (an efficient homomorphic encryption), and Sparsification. Empirical experiments conducted under the three protection mechanisms demonstrate the effectiveness of our proposed algorithms. [ABSTRACT FROM AUTHOR]

As AI systems have obtained significant performance to be deployed widely in our daily lives and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI systems good enough and trustworthy, plenty of researches have been done to build guidelines for trustworthy AI systems. Machine learning is one of the most important parts of AI systems, and representation learning is the fundamental technology in machine learning. How to make representation learning trustworthy in real-world application, e.g., cross domain scenarios, is very valuable and necessary for both machine learning and AI system fields. Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework, which includes four concepts, i.e., robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction. Specifically, we first introduce the details of the proposed trustworthy framework for representation learning across domains. Second, we provide basic notions and comprehensively summarize existing methods for the trustworthy framework from four concepts. Finally, we conclude this survey with insights and discussions on future research directions. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) provides a novel paradigm for privacy-preserving machine learning, enabling multiple clients to collaborate on model training without sharing private data. To handle multi-source heterogeneous data, Vertical Federated Learning (VFL) has been extensively investigated. However, in the context of VFL, the label information tends to be kept in one authoritative client and is very limited. This poses two challenges for model training in the VFL scenario. On the one hand, a small number of labels cannot guarantee to train a well VFL model with informative network parameters, resulting in unclear boundaries for classification decisions. On the other hand, the large amount of unlabeled data is dominant and should not be discounted, and it is worthwhile to focus on how to leverage them to improve representation modeling capabilities. To address the preceding two challenges, we first introduce supervised contrastive loss to enhance the intra-class aggregation and inter-class estrangement, which is to deeply explore label information and improve the effectiveness of downstream classification tasks. Then, for unlabeled data, we introduce a pseudo-label-guided consistency mechanism to induce the classification results coherent across clients, which allows the representations learned by local networks to absorb the knowledge from other clients, and alleviates the disagreement between different clients for classification tasks. We conduct sufficient experiments on four commonly used datasets, and the experimental results demonstrate that our method is superior to the state-of-the-art methods, especially in the low-label rate scenario, and the improvement becomes more significant. [ABSTRACT FROM AUTHOR]

In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of privacy leakage cannot be ignored in the presence of semi-honest adversaries. Existing research has focused either on designing protection mechanisms or on inventing attacking mechanisms. While the battle between defenders and attackers seems never-ending, we are concerned with one critical question: Is it possible to prevent potential attacks in advance? To address this, we propose the first game-theoretic framework that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks. We name this game the federated learning privacy game (FLPG), in which neither defenders nor attackers are aware of all participants' payoffs. To handle the incomplete information inherent in this situation, we propose associating the FLPG with an oracle that has two primary responsibilities. First, the oracle provides lower and upper bounds of the payoffs for the players. Second, the oracle acts as a correlation device, privately providing suggested actions to each player. With this novel framework, we analyze the optimal strategies of defenders and attackers. Furthermore, we derive and demonstrate conditions under which the attacker, as a rational decision-maker, should always follow the oracle's suggestion not to attack. [ABSTRACT FROM AUTHOR]

Trustworthy federated learning typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency reduction while protecting data privacy. Therefore, protection mechanisms and their parameters should be carefully chosen to strike an optimal tradeoff among privacy leakage, utility loss, and efficiency reduction. To this end, federated learning practitioners need tools to measure the three factors and optimize the tradeoff between them to choose the protection mechanism that is most appropriate to the application at hand. Motivated by this requirement, we propose a framework that (1) formulates trustworthy federated learning as a problem of finding a protection mechanism to optimize the tradeoff among privacy leakage, utility loss, and efficiency reduction and (2) formally defines bounded measurements of the three factors. We then propose a meta-learning algorithm to approximate this optimization problem and find optimal protection parameters for representative protection mechanisms, including randomization, homomorphic encryption, secret sharing, and compression. We further design estimation algorithms to quantify these found optimal protection parameters in a practical horizontal federated learning setting and provide a theoretical analysis of the estimation error. [ABSTRACT FROM AUTHOR]

Vertical federated learning (VFL) revolutionizes privacy-preserved collaboration for small businesses that have distinct but complementary feature sets. However, as the scope of VFL expands, the constant entering and leaving of participants and the subsequent exercise of the "right to be forgotten" pose a great challenge in practice. The question of how to efficiently erase one's contribution from the shared model remains largely unexplored in the context of VFL. In this article, we introduce a vertical federated unlearning framework, which integrates model checkpointing techniques with a hybrid, first-order optimization technique. The core concept is to reduce backpropagation time and improve convergence/generalization by combining the advantages of the existing optimizers. We provide in-depth theoretical analysis and time complexity to illustrate the effectiveness of the proposed design. We conduct extensive experiments on six public datasets and demonstrate that our method could achieve up to 6.3× speedup compared to the baseline, with negligible influence on the original learning task. [ABSTRACT FROM AUTHOR]

Nowadays, with the advancement of technology, many retail companies require in-house data scientist teams to build machine learning tasks, such as user segmentation and item price prediction. These teams typically use a trial-and-error process to obtain a good model for a given dataset and machine learning task, which is time-consuming and requires expertise. However, the team may have built models for other tasks on different datasets. This article proposes a framework to obtain a model architecture using the previous solved machine learning tasks and datasets. By analyzing real datasets with over 70,000 images from 11 online retail e-commerce websites, it is demonstrated that the performance of a model is related to the similarity among datasets, models, and machine learning tasks. A framework is hence proposed to obtain the model using the similarities among them. It was proven that the model was 26.6% better in accuracy, and using only 20% of the runtime while comparing to an auto network architecture search library, Auto-Keras, in predicting the attributes of fashion images. To the best of our knowledge, this is the first article to obtain the best model based on the similarity among machine learning tasks, models, and datasets. [ABSTRACT FROM AUTHOR]

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving privacy and maintaining high model utility. In addition, it is a mandate for a federated learning system to achieve high efficiency in order to enable large-scale model training and deployment. We propose a unified federated learning framework that reconciles horizontal and vertical federated learning. Based on this framework, we formulate and quantify the trade-offs between privacy leakage, utility loss, and efficiency reduction, which leads us to the No-Free-Lunch (NFL) theorem for the federated learning system. NFL indicates that it is unrealistic to expect an FL algorithm to simultaneously provide excellent privacy, utility, and efficiency in certain scenarios. We then analyze the lower bounds for the privacy leakage, utility loss, and efficiency reduction for several widely-adopted protection mechanisms, including Randomization, Homomorphic Encryption, Secret Sharing, and Compression. Our analysis could serve as a guide for selecting protection parameters to meet particular requirements. [ABSTRACT FROM AUTHOR]

Solid‐state electrolytes hold great promise for lithium‐based batteries with high energy density and safety. Here, novel metal‐organic frameworks (MOFs) based composite membranes were fabricated by a rolling process and subsequently employed as quasi solid‐state electrolytes, exhibiting improved ionic conductivity and Li+ transference number as well as stable electrochemical window. Furthermore, the MOF‐based membranes presented a significant effect in modulating the stripping/plating process of Li and resulted in a dendrite‐free Li deposition. The corresponding LiFePO4|Li batteries were assembled and presented improved rate capability and high Coulombic efficiency, offering a new option for MOF‐based electrolytes. [ABSTRACT FROM AUTHOR]

The vast potential of organic materials for electronic, optoelectronic and spintronic devices entails substantial interest in the fabrication of π-conjugated systems with tailored functionality directly at insulating interfaces. On-surface fabrication of such materials on non-metal surfaces remains to be demonstrated with high yield and selectivity. Here we present the synthesis of polyaromatic chains on metallic substrates, insulating layers, and in the solid state. Scanning probe microscopy shows the formation of azaullazine repeating units on Au(111), Ag(111), and h-BN/Cu(111), stemming from intermolecular homo-coupling via cycloaddition reactions of CN-substituted polycyclic aromatic azomethine ylide (PAMY) intermediates followed by subsequent dehydrogenation. Matrix-assisted laser desorption/ionization (MALDI) mass spectrometry demonstrates that the reaction also takes place in the solid state in the absence of any catalyst. Such intermolecular cycloaddition reactions are promising methods for direct synthesis of regioregular polyaromatic polymers on arbitrary insulating surfaces. A critical milestone for the advancement of nanoscale organic circuitry is the fabrication of well-defined conjugated polymers on non-metal substrates. Here, the authors demonstrate extended polycyclic aromatic chains from repetitive cycloadditions which form not only on metals, but also on boron nitride layers and in the solid state. [ABSTRACT FROM AUTHOR]