Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis

Visual sentiment analysis has received increasing attention in recent years. However, the quality of the dataset is a concern because the sentiment labels are crowd-sourcing, subjective, and prone to mistakes. This poses a severe threat to the data-driven models including the deep neural networks which would generalize poorly on the testing cases if they are trained to over-fit the samples with noisy sentiment labels. Inspired by the recent progress on learning with noisy labels, we propose a robust learning method to perform robust visual sentiment analysis. Our method relies on an external memory to aggregate and filter noisy labels during training and thus can prevent the model from overfitting the noisy cases. The memory is composed of the prototypes with corresponding labels, both of which can be updated online. We establish a benchmark for visual sentiment analysis with label noise using publicly available datasets. The experiment results of the proposed benchmark settings comprehensively show the effectiveness of our method.

Federated Learning of Molecular Properties in a Heterogeneous Setting

Chemistry research has both high material and computational costs to conduct experiments. Institutions thus consider chemical data to be valuable and there have been few efforts to construct large public datasets for machine learning. Another challenge is that different intuitions are interested in different classes of molecules, creating heterogeneous data that cannot be easily joined by conventional distributed training. In this work, we introduce federated heterogeneous molecular learning to address these challenges. Federated learning allows end-users to build a global model collaboratively while preserving the training data distributed over isolated clients. Due to the lack of related research, we first simulate a federated heterogeneous benchmark called FedChem. FedChem is constructed by jointly performing scaffold splitting and Latent Dirichlet Allocation on existing datasets. Our results on FedChem show that significant learning challenges arise when working with heterogeneous molecules. We then propose a method to alleviate the problem, namely Federated Learning by Instance reweighTing (FLIT). FLIT can align the local training across heterogeneous clients by improving the performance for uncertain samples. Comprehensive experiments conducted on our new benchmark FedChem validate the advantages of this method over other federated learning schemes. FedChem should enable a new type of collaboration for improving AI in chemistry that mitigates concerns about valuable chemical data.

Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization

Deep learning algorithms mine knowledge from the training data and thus would likely inherit the datasets bias information. As a result, the obtained model would generalize poorly and even mislead the decision process in real-life applications. We propose to remove the bias information misused by the target task with a cross-sample adversarial debiasing (CSAD) method. CSAD explicitly extracts target and bias features disentangled from the latent representation generated by a feature extractor and then learns to discover and remove the correlation between the target and bias features. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. Moreover, we propose joint content and local structural representation learning to boost mutual information estimation for better performance. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.

TWAG: A Topic-Guided Wikipedia Abstract Generator

Wikipedia abstract generation aims to distill a Wikipedia abstract from web sources and has met significant success by adopting multi-document summarization techniques. However, previous works generally view the abstract as plain text, ignoring the fact that it is a description of a certain entity and can be decomposed into different topics. In this paper, we propose a two-stage model TWAG that guides the abstract generation with topical information. First, we detect the topic of each input paragraph with a classifier trained on existing Wikipedia articles to divide input documents into different topics. Then, we predict the topic distribution of each abstract sentence, and decode the sentence from topic-aware representations with a Pointer-Generator network. We evaluate our model on the WikiCatSum dataset, and the results show that modelnames outperforms various existing baselines and is capable of generating comprehensive abstracts. Our code and dataset can be accessed at url{https://github.com/THU-KEG/TWAG}

Quantum oscillations, Magnetic breakdown and thermal Hall effect in Co$_3$Sn$_2$S$_2$

Co$_3$Sn$_2$S$_2$ is a ferromagnetic semi-metal with Weyl nodes in its band structure and a large anomalous Hall effect below its Curie temperature of 177 K. We present a detailed study of its Fermi surface and examine the relevance of the anomalous transverse Wiedemann Franz law to it. We studied Shubnikov-de Haas oscillations along two orientations in single crystals with a mobility as high as $2.7times$10$^3$ cm$^2$V$^{-1}$s$^{-1}$ subject to a magnetic field as large as $sim$ 60 T. The angle dependence of the frequencies is in agreement with density functional theory (DFT) calculations and reveals two types of hole pockets (H1, H2) and two types of electron pockets (E1, E2). An additional unexpected frequency emerges at high magnetic field. We attribute it to magnetic breakdown between the hole pocket H2 and the electron pocket E2, since it is close to the sum of the E2 and H2 fundamental frequencies. By measuring the anomalous thermal and electrical Hall conductivities, we quantified the anomalous transverse Lorenz ratio, which is close to the Sommerfeld ratio ($L_0=frac{pi^2}{3}frac{k_B^2}{e^2}$) below 100 K and deviates downwards at higher temperatures. This finite temperature deviation from the anomalous Wiedemann-Franz law is a source of information on the distance between the sources and sinks of the Berry curvature and the chemical potential.

Near-perfect fidelity polarization-encoded multilayer optical data storage based on aligned gold nanorods

Encoding information in light polarization is of great importance in facilitating optical data storage (ODS) for information security and data storage capacity escalation. However, despite recent advances in nanophotonic techniques vastly enhancing the feasibility of applying polarization channels, the data fidelity in reconstructed bits has been constrained by severe crosstalks occurring between varied polarization angles during data recording and reading process, which gravely hindered the utilization of this technique in practice. In this paper, we demonstrate an ultra-low crosstalk polarization-encoding multilayer optical data storage technique for high-fidelity data recording and retrieving by utilizing a nanofibre-based nanocomposite film involving highly aligned gold nanorods (GNRs). With parallelizing the gold nanorods in the recording medium, the information carrier configuration minimizes miswriting and misreading possibilities for information input and output, respectively, compared with its randomly self-assembled counterparts. The enhanced data accuracy has significantly improved the bit recall fidelity that is quantified by a correlation coefficient higher than 0.99. It is anticipated that the demonstrated technique can facilitate the development of multiplexing ODS for a greener future.

Fairness-aware Personalized Ranking Recommendation via Adversarial Learning

Recommendation algorithms typically build models based on historical user-item interactions (e.g., clicks, likes, or ratings) to provide a personalized ranked list of items. These interactions are often distributed unevenly over different groups of items due to varying user preferences. However, we show that recommendation algorithms can inherit or even amplify this imbalanced distribution, leading to unfair recommendations to item groups. Concretely, we formalize the concepts of ranking-based statistical parity and equal opportunity as two measures of fairness in personalized ranking recommendation for item groups. Then, we empirically show that one of the most widely adopted algorithms -- Bayesian Personalized Ranking -- produces unfair recommendations, which motivates our effort to propose the novel fairness-aware personalized ranking model. The debiased model is able to improve the two proposed fairness metrics while preserving recommendation performance. Experiments on three public datasets show strong fairness improvement of the proposed model versus state-of-the-art alternatives. This is paper is an extended and reorganized version of our SIGIR 2020~cite{zhu2020measuring} paper. In this paper, we re-frame the studied problem as `item recommendation fairness in personalized ranking recommendation systems, and provide more details about the training process of the proposed model and details of experiment setup.

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels

The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding anchor points or their approximates, defined as instances belonging to a particular class almost surely. Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points. In this paper, we propose an alternative option to the above task. Our main contribution is the discovery of an efficient estimation procedure based on a clusterability condition. We prove that with clusterable representations of features, using up to third-order consensuses of noisy labels among neighbor representations is sufficient to estimate a unique transition matrix. Compared with methods using anchor points, our approach uses substantially more instances and benefits from a much better sample complexity. We demonstrate the estimation accuracy and advantages of our estimates using both synthetic noisy labels (on CIFAR-10/100) and real human-level noisy labels (on Clothing1M and our self-collected human-annotated CIFAR-10). Our code and human-level noisy CIFAR-10 labels are available at https://github.com/UCSC-REAL/HOC.

Critical point for Bose-Einstein condensation of excitons in graphite

An exciton is an electron-hole pair bound by attractive Coulomb interaction. Short-lived excitons have been detected by a variety of experimental probes in numerous contexts. An excitonic insulator, a collective state of such excitons, has been more elusive. Here, thanks to Nernst measurements in pulsed magnetic fields, we show that in graphite there is a critical temperature (T = 9.2 K) and a critical magnetic field (B = 47 T) for Bose-Einstein condensation of excitons. At this critical field, hole and electron Landau sub-bands simultaneously cross the Fermi level and allow exciton formation. By quantifying the effective mass and the spatial separation of the excitons in the basal plane, we show that the degeneracy temperature of the excitonic fluid corresponds to this critical temperature. This identification would explain why the field-induced transition observed in graphite is not a universal feature of three-dimensional electron systems pushed beyond the quantum limit.

Planar Hall effect caused by the memory of antiferromagnetic domain walls in Mn$_3$Ge

In Mn$_3$X (X=Sn, Ge) antiferromagnets domain walls are thick and remarkably complex because of the non-collinear arrangement of spins in each domain. A planar Hall effect (PHE), an electric field perpendicular to the applied current but parallel to the applied magnetic field, was recently observed inside the hysteresis loop of Mn$_3$Sn. The sign of the PHE displayed a memory tuned by the prior orientation of the magnetic field and its history. We present a study of PHE in Mn$_3$Ge extended from room temperature down to 2 K and show that this memory effect can be manipulated by either magnetic field or thermal cycling. We show that the memory can be wiped out if the prior magnetic field exceeds 0.8 T or when the temperature exceeds $T_mathrm{N}$. We also find a detectable difference between the amplitude of PHE with zero-field and field thermal cycling. The ratio between the PHE and the anomalous Hall effect (AHE) decreases slightly as temperature is increased from 2 K to $T_{rm{N}}$, tracks the temperature dependence of magnetization. This erasable memory effect may be used for data storage.