Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations.

Graph contrastive learning (GCL) is a promising direction toward alleviating the label dependence, poor generalization and weak robustness of graph neural networks, learning representations with invariance, and discriminability by solving pretasks. The pretasks are mainly built on mutual information estimation, which requires data augmentation to construct positive samples with similar semantics to learn invariant signals and negative samples with dissimilar semantics to empower representation discriminability. However, an appropriate data augmentation configuration depends heavily on lots of empirical trials such as choosing the compositions of data augmentation techniques and the corresponding hyperparameter settings. We propose an augmentation-free GCL method, invariant-discriminative GCL (iGCL), that does not intrinsically require negative samples. iGCL designs the invariant-discriminative loss (ID loss) to learn invariant and discriminative representations. On the one hand, ID loss learns invariant signals by directly minimizing the mean square error (MSE) between the target samples and positive samples in the representation space. On the other hand, ID loss ensures that the representations are discriminative by an orthonormal constraint forcing the different dimensions of representations to be independent of each other. This prevents representations from collapsing to a point or subspace. Our theoretical analysis explains the effectiveness of ID loss from the perspectives of the redundancy reduction criterion, canonical correlation analysis (CCA), and information bottleneck (IB) principle. The experimental results demonstrate that iGCL outperforms all baselines on five node classification benchmark datasets. iGCL also shows superior performance for different label ratios and is capable of resisting graph attacks, which indicates that iGCL has excellent generalization and robustness. The source code is available at https://github.com/lehaifeng/ T-GCN/tree/master/iGCL.

Analysis of the causes of inferiority feelings based on social media data with Word2Vec.

Feelings of inferiority are complex emotions that usually indicate perceived weakness and helplessness. A lack of timely and effective interventions may bring serious consequences to individuals with inferiority feelings. Due to privacy concerns, those people often hesitate to seek face-to-face help, but they usually spontaneously share their feelings on social media, which makes social media a good resource for ample inferiority-related data. We randomly selected a sample of posts indicating inferiority feelings to explore the causes of inferiority. Through language analysis and natural language processing, we constructed a Word2Vec model of inferiority based on social media data and applied it to the cause analysis of inferiority feelings. The main causes of inferiority feelings are personal experience, social interaction, love relationship, etc. People feeling inferior about their personal experiences usually are largely influenced by their ways of thinking and life attitudes. Social and emotional factors overlap somewhat in the development of inferiority. In love relationships, males are more prone to inferiority feeling than females. These findings will help relevant institutions and organizations better understand people with inferiority feelings and facilitate the development of targeted treatment for those with potential self-esteem problems.

Structure analysis and antimutagenic activity of a novel salt-soluble polysaccharide from Auricularia polytricha.

BACKGROUND: Auricularia polytricha is known to be a highly nutritious foodstuff. We report here the purification, structure characterization and antimutagenic activity in vivo of a 0.9% NaCl solution-soluble polysaccharide (SSP) from the mycelia of A. polytricha. RESULTS: Analysis by high-performance liquid chromatography coupled to a TSK-G5000PWXL column and gel filtration chromatography on Sephacryl S-400 HR indicated that SSP is homogeneous with an average molecular weight of about 9.30 × 10(5) Da. The structure of SSP was revealed by chemical methods, Fourier transform infrared spectroscopy and nuclear magnetic resonance spectroscopy. Results indicated that SSP is a glucan consisting of a1,3-ß-glucan, 1,6-α-glucan, 1,4-α-glucan and 1,3-α-glucan backbone with a single 1,6-α-d-glucopyranosyl side-branching unit on every nine residues, on average, along the main chain. Atomic force microscopy indicates the presence of macromolecular species in morphology and shows a clear association of prolate particle. Meanwhile, SSP was found to significantly preventing micronuclei in polychromatic erythrocytes and reticulocytes of mice (P < 0.01). CONCLUSION: These results indicate that polysaccharide SSP from A. polytricha exhibits antimutagenic activity against the in vivo DNA-damaging effect of the indirectly acting alkylating agent cyclophosphamide.