Frequency Domain-Oriented Complex Graph Neural Networks for Graph Classification.

Graph neural networks (GNNs) could directly deal with the data of graph structure. Current GNNs are confined to the spatial domain and learn real low-dimensional embeddings in graph classification tasks. In this article, we explore frequency domain-oriented complex GNNs in which the node's embedding in each layer is a complex vector. The difficulty lies in the design of graph pooling and we propose a mirror-connected design with two crucial problems: parameter reduction problem and complex gradient backpropagation problem. To deal with the former problem, we propose the notion of squared singular value pooling (SSVP) and prove that the representation power of SSVP followed by a fully connected layer with nonnegative weights is exactly equivalent to that of a mirror-connected layer. To resolve the latter problem, we provide an alternative feasible method to solve singular values of complex embeddings with a theoretical guarantee. Finally, we propose a mixture of pooling strategies in which first-order statistics information is employed to enrich the last low-dimensional representation. Experiments on benchmarks demonstrate the effectiveness of the complex GNNs with mirror-connected layers.

HMM-GDAN: Hybrid multi-view and multi-scale graph duplex-attention networks for drug response prediction in cancer.

Precision medicine is devoted to discovering personalized therapy for complex and difficult diseases like cancer. Many machine learning approaches have been developed for drug response prediction towards precision medicine. Notwithstanding, genetic profiles based multi-view graph learning schemes have not yet been explored for drug response prediction in previous works. Furthermore, multi-scale latent feature fusion is not considered sufficiently in the existing frameworks of graph neural networks (GNNs). Previous works on drug response prediction mainly depend on sequence data or single-view graph data. In this paper, we propose to construct multi-view graph by means of multi-omics data and STRING protein-protein association data, and develop a new architecture of GNNs for drug response prediction in cancer. Specifically, we propose hybrid multi-view and multi-scale graph duplex-attention networks (HMM-GDAN), in which both multi-view self-attention mechanism and view-level attention mechanism are devised to capture the complementary information of views and emphasize on the importance of each view collaboratively, and rich multi-scale features are constructed and integrated to further form high-level representations for better prediction. Experiments on GDSC2 dataset verify the superiority of the proposed HMM-GDAN when compared with state-of-the-art baselines. The effectiveness of multi-view and multi-scale strategies is demonstrated by the ablation study.

Rebalanced Zero-Shot Learning.

Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer unseen classes. However, we find that such existing models mostly produce imbalanced semantic predictions, i.e. these models could perform precisely for some semantics, but may not for others. To address the drawback, we aim to introduce an imbalanced learning framework into ZSL. However, we find that imbalanced ZSL has two unique challenges: (1) Its imbalanced predictions are highly correlated with the value of semantic labels rather than the number of samples as typically considered in the traditional imbalanced learning; (2) Different semantics follow quite different error distributions between classes. To mitigate these issues, we first formalize ZSL as an imbalanced regression problem which offers empirical evidences to interpret how semantic labels lead to imbalanced semantic predictions. We then propose a re-weighted loss termed Re-balanced Mean-Squared Error (ReMSE), which tracks the mean and variance of error distributions, thus ensuring rebalanced learning across classes. As a major contribution, we conduct a series of analyses showing that ReMSE is theoretically well established. Extensive experiments demonstrate that the proposed method effectively alleviates the imbalance in semantic prediction and outperforms many state-of-the-art ZSL methods.

Tensor Learning Meets Dynamic Anchor Learning: From Complete to Incomplete Multiview Clustering.

Multiview clustering (MVC), which can dexterously uncover the underlying intrinsic clustering structures of the data, has been particularly attractive in recent years. However, previous methods are designed for either complete or incomplete multiview only, without a unified framework that handles both tasks simultaneously. To address this issue, we propose a unified framework to efficiently tackle both tasks in approximately linear complexity, which integrates tensor learning to explore the inter-view low-rankness and dynamic anchor learning to explore the intra-view low-rankness for scalable clustering (TDASC). Specifically, TDASC efficiently learns smaller view-specific graphs by anchor learning, which not only explores the diversity embedded in multiview data, but also yields approximately linear complexity. Meanwhile, unlike most current approaches that only focus on pair-wise relationships, the proposed TDASC incorporates multiple graphs into an inter-view low-rank tensor, which elegantly models the high-order correlations across views and further guides the anchor learning. Extensive experiments on both complete and incomplete multiview datasets clearly demonstrate the effectiveness and efficiency of TDASC compared with several state-of-the-art techniques.

I3 - /I- Redox Reaction-mediated Organic Zinc-Air Batteries with Accelerated Kinetics and Long Shelf Lives.

The storage time of Zn-air batteries (ZABs) for practical implementation have been neglected long-lastingly. ZABs based on organic solvents promise long shelf lives but suffer from sluggish kinetics. Here, we report a longly storable ZAB with accelerated kinetics mediated by I3 - /I- redox. In the charge process, the electrooxidation of Zn5 (OH)8 Cl2 ⋅H2 O is accelerated by I3 - chemical oxidation. In the discharge process, I- adsorbed on the electrocatalyst changes the energy level of oxygen reduction reaction (ORR). Benefitting from these advantages, the prepared ZAB shows remarkably improved round-trip efficiency (56.03 % vs. 30.97 % without the mediator), and long-term cycling time (>2600 h) in ambient air without replacing any components or applying any protective treatment to Zn anode and electrocatalyst. After resting for 30 days without any protection, it can still directly discharge continuously for 32.5 h and charge/discharge very stably for 2200 h (440 cycles), which is evidently superior to aqueous ZABs (only 0/0.25 h, and 50/25 h (10/5 cycles) by mild/alkaline electrolyte replenishment). This study provides a strategy to solve both storage and sluggish kinetics issues that have been plaguing ZABs for centuries, opening up a new avenue to the industrial application of ZABs.

p-n hybrid bulk heterojunction enables enhanced photothermoelectric performance with UV-Vis-NIR light.

Infrared light accounts for the vast majority of natural light energy, however, the challenge of converting infrared light directly into electricity is too difficult. The photothermoelectric (PTE) effect (connecting the photothermal (PT) and thermoelectric (TE) effects) provides a feasible solution for the indirect conversion of infrared light into electrical energy. Therefore, it is of great significance to actively seek and explore materials with good PT and TE performance to fully harvest infrared light energy. Here, we prepared an organic-inorganic hybrid bulk heterojunction film by combining poly(3,4-ethylene-dioxythiophene):polystyrenesulphonate (PEDOT:PSS) and ZnO nanowires (ZnO-NWs). This common composite strategy is able to utilize the ultra-wide spectrum ranging from ultraviolet-visible (UV-Vis) to near-infrared (NIR) light to realize light-to-electricity conversion based on the PTE effect. ZnO-NWs can not only increase the Seebeck coefficient of PEDOT:PSS, but also enhance the absorption of the hybrid film under the NIR light. Thereby, the enhancement of the photothermal-induced voltage was achieved due to the separation of generated electron-hole pairs in the built-in electric field induced by a photothermal gradient. This study provides a new suggestion for improving the PTE performance of the material and making better use of solar energy.

Organic/Inorganic Hybrid Boosting Energy Harvesting Based on the Photothermoelectric Effect.

Attracted by the capability of light to heat and electricity conversion, the photothermoelectric (PTE) effect has drawn great attention in the field of energy conversion and self-powered electronics. However, it still requires effective strategies to convert electricity from light based on the corresponding photothermoelectric generator. Herein, considering the broad photoresponse and large Seebeck effect of tellurium nanowires (Te NWs) as well as the high electrical conductivity of poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate) (PEDOT:PSS), PEDOT:PSS/Te NW hybrid thin films were fabricated to enhance the conversion efficiency by the photothermoelectric effect with respect to single thermoelectric performance. A detailed comparison has been achieved between the photothermoelectric and thermoelectric properties induced by light illumination and heating plates through current-voltage (I-V) transport, respectively. PEDOT:PSS/Te NW hybrid films also show an enhanced photothermal harvesting compared to pure PEDOT:PSS. A photothermoelectric device was assembled based on the as-fabricated PEDOT:PSS/Te NW hybrid films with 90 wt% Te NWs and achieved a competitive output power density with good stability, which may provide insights into improving solar energy harvesting-based photothermoelectric conversion by organic/inorganic hybrids.

LogDet Metric-Based Domain Adaptation.

Domain adaptation has proven to be successful in dealing with the case where training and test samples are drawn from two kinds of distributions, respectively. Recently, the second-order statistics alignment has gained significant attention in the field of domain adaptation due to its superior simplicity and effectiveness. However, researchers have encountered major difficulties with optimization, as it is difficult to find an explicit expression for the gradient. Moreover, the used transformation employed here does not perform dimensionality reduction. Accordingly, in this article, we prove that there exits some scaled LogDet metric that is more effective for the second-order statistics alignment than the Frobenius norm, and hence, we consider it for second-order statistics alignment. First, we introduce the two homologous transformations, which can help to reduce dimensionality and excavate transferable knowledge from the relevant domain. Second, we provide an explicit gradient expression, which is an important ingredient for optimization. We further extend the LogDet model from single-source domain setting to multisource domain setting by applying the weighted Karcher mean to the LogDet metric. Experiments on both synthetic and realistic domain adaptation tasks demonstrate that the proposed approaches are effective when compared with state-of-the-art ones.

Homologous Component Analysis for Domain Adaptation.

Covariate shift assumption based domain adaptation approaches usually utilize only one common transformation to align marginal distributions and make conditional distributions preserved. However, one common transformation may cause loss of useful information, such as variances and neighborhood relationship in both source and target domain. To address this problem, we propose a novel method called homologous component analysis (HCA) where we try to find two totally different but homologous transformations to align distributions with side information and make conditional distributions preserved. As it is hard to find a closed form solution to the corresponding optimization problem, we solve them by means of the alternating direction minimizing method (ADMM) in the context of Stiefel manifolds. We also provide a generalization error bound for domain adaptation in semi-supervised case and two transformations can help to decrease this upper bound more than only one common transformation does. Extensive experiments on synthetic and real data show the effectiveness of the proposed method by comparing its classification accuracy with the state-of-the-art methods and numerical evidence on chordal distance and Frobenius distance shows that resulting optimal transformations are different.

Efficient DMSO-Vapor Annealing for Enhancing Thermoelectric Performance of PEDOT:PSS-Based Aerogel.

Conducting polymer-based composite aerogel film is desired to be used as thermoelectric (TE) materials due to its good flexibility and ultralow thermal conductivity. Here, we proposed the simple freeze drying method to fabricate free-standing poly(3,4-ethylenedioxythiophene)/poly(styrenesulfonate) (PEDOT:PSS)-based aerogel films without any crosslinker addition. The evolutions of morphology and TE performance were systemically investigated with various organic solvent addition. Furthermore, a series of the PEDOT:PSS/tellurium nanowires (Te-NWs) composite aerogel films was prepared, and the relationship between the structure and the charge-transport mechanism of the binary complex system was explored based on series and parallel models. Finally, an efficient dimethyl sulfoxide-vapor annealing was employed to further optimize the TE performance of PEDOT:PSS/Te-NWs composite aerogel films. The ZT value was estimated to be 2.0 × 10-2 at room temperature. On the basis of the flexibility and highly enhanced TE performance, a prototype TE generator consisting of p-type PEDOT:PSS/Te-NWs aerogel films and n-type carbon nanotube fibers as legs has been fabricated with an acceptable output power of 1.28 µW at a temperature gradient of 60 K, which could be potentially applied in wearable electronics.