No abstract

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the samplewise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a generalized class-wise representation, by innovatively leveraging the dynamic routing algorithm in meta-learning. In this way, we find the model is able to induce and generalize better. We evaluate the proposed model on a well-studied sentiment classification dataset (English) and a real-world dialogue intent classification dataset (Chinese). Experiment results show that on both datasets, the proposed model significantly outperforms the existing state-of-the-art approaches, proving the effectiveness of class-wise generalization in few-shot text classification. * * Corresponding authors: Y.Li and P.Jian.

In this paper, we develop several related finite dimensional variational principles for discrete optimal transport (DOT), Minkowski type problems for convex polytopes and discrete Monge-Ampere equation (DMAE). A link between the discrete optimal transport, discrete Monge-Ampere equation and the power diagram in computational geometry is established.

Fe–Ni alloy nanoparticles with various alloy components were fabricated by a direct current arc-discharge method. By dispersing the nanoparticles homogeneously into a paraffin matrix, the complex permittivity (εr=εr′+iεr″) and permeability (μr=μr′+iμr″) of the nanoparticles have been investigated in the frequency range of 2–18 GHz and the effects of alloy components on the electromagnetic parameters were discussed. It is found that the permittivities of the nanoparticles are lower than those of the microscale counterparts and almost independent of frequency. The magnetic loss is attributed to natural resonance and the resonance peak shifts to high frequency range with the increase in Fe content. Better microwave absorption performances can be obtained by adjusting the composition and tailoring the core/shell structures to balance the electromagnetic parameters. The calculated results indicate that the Fe–Ni nanoparticles with 49 wt % Ni exhibit excellent electromagnetic wave (EMW) absorption properties (reflection loss <−20 dB) over the range of 7.6–16.0 GHz in the thickness of 1.02–1.70 mm. The mechanism of effective EMW introduction and attenuation is discussed on the basis of the experimental results.