Search

The paper discusses signed graphs, which model friendly or antagonistic relationships using edges marked with positive or negative signs, focusing on the task of link sign prediction. While Signed Graph Neural Networks (SGNNs) have advanced, they face challenges like graph sparsity and unbalanced triangles. The authors propose using data augmentation (DA) techniques to address these issues, although many existing methods are not suitable for signed graphs due to a lack of side information. They highlight that the random DropEdge method, a rare DA approach applicable to signed graphs, does not enhance link sign prediction performance. In response, they introduce the Signed Graph Augmentation (SGA) framework, which includes a structure augmentation module to identify candidate edges and a strategy for selecting beneficial candidates, ultimately improving SGNN training. Experimental results show that SGA significantly boosts the performance of SGNN models, with a notable 32.3% improvement in F1-micro for SGCN on the Slashdot dataset., Comment: NeurIPS 2024

The chiral magnetic effect (CME) in heavy-ion collisions reflects the local violation of ${\cal P}$ and ${\cal CP}$ symmetries in strong interactions and manifests as electric charge separation along the direction of the magnetic field created by the wounded nuclei. The experimental observables for the CME, such as the $\gamma_{112}$ correlator, the $R_{\Psi_2}(\Delta S)$ correlator, and the signed balance functions, however, are also subject to non-CME backgrounds, including those from resonance decays. A previous study showed that the CME observables are affected by the diagonal component of the spin density matrix, the $\rho_{00}$ for vector mesons. In this work, we study the contributions from the other elements of the spin density matrix using a toy model and a multiphase transport model. We find that the real part of the $\rho_{1-1}$ component, $\mathrm{Re}\,\rho_{1-1}$, affects the CME observables in a manner opposite to that of the $\rho_{00}$. All three aforementioned CME observables show a linear dependence on $\mathrm{Re}\,\rho_{1-1}$ in the model calculations, supporting our analytical derivations. The rest elements of the spin density matrix do not contribute to the CME observables. The off-diagonal terms in the spin density matrix indicate spin coherence and may be nonzero in heavy-ion collisions due to local spin polarization or spin-spin correlations. Thus, $\mathrm{Re}\,\rho_{1-1}$, along with $\rho_{00}$, could play a significant role in interpreting measurements in search of the CME.

This work introduces approaches to assessing phrase breaks in ESL learners' speech using pre-trained language models (PLMs) and large language models (LLMs). There are two tasks: overall assessment of phrase break for a speech clip and fine-grained assessment of every possible phrase break position. To leverage NLP models, speech input is first force-aligned with texts, and then pre-processed into a token sequence, including words and phrase break information. To utilize PLMs, we propose a pre-training and fine-tuning pipeline with the processed tokens. This process includes pre-training with a replaced break token detection module and fine-tuning with text classification and sequence labeling. To employ LLMs, we design prompts for ChatGPT. The experiments show that with the PLMs, the dependence on labeled training data has been greatly reduced, and the performance has improved. Meanwhile, we verify that ChatGPT, a renowned LLM, has potential for further advancement in this area., Comment: Accepted by InterSpeech 2023. arXiv admin note: substantial text overlap with arXiv:2210.16029

In the assignment problem, a set of items must be allocated to unit-demand agents who express ordinal preferences (rankings) over the items. In the assignment problem with priorities, agents with higher priority are entitled to their preferred goods with respect to lower priority agents. A priority can be naturally represented as a ranking and an uncertain priority as a distribution over rankings. For example, this models the problem of assigning student applicants to university seats or job applicants to job openings when the admitting body is uncertain about the true priority over applicants. This uncertainty can express the possibility of bias in the generation of the priority ranking. We believe we are the first to explicitly formulate and study the assignment problem with uncertain priorities. We introduce two natural notions of fairness in this problem: stochastic envy-freeness (SEF) and likelihood envy-freeness (LEF). We show that SEF and LEF are incompatible and that LEF is incompatible with ordinal efficiency. We describe two algorithms, Cycle Elimination (CE) and Unit-Time Eating (UTE) that satisfy ordinal efficiency (a form of ex-ante Pareto optimality) and SEF; the well known random serial dictatorship algorithm satisfies LEF and the weaker efficiency guarantee of ex-post Pareto optimality. We also show that CE satisfies a relaxation of LEF that we term 1-LEF which applies only to certain comparisons of priority, while UTE satisfies a version of proportional allocations with ranks. We conclude by demonstrating how a mediator can model a problem of school admission in the face of bias as an assignment problem with uncertain priority., Comment: Accepted to AAMAS 2023

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power of PLMs. There are two sub-tasks: overall assessment of phrase break for a speech clip; fine-grained assessment of every possible phrase break position. Speech input is first force-aligned with texts, then pre-processed to a token sequence, including words and associated phrase break information. The token sequence is then fed into the pre-training and fine-tuning pipeline. In pre-training, a replaced break token detection module is trained with token data where each token has a certain percentage chance to be randomly replaced. In fine-tuning, overall and fine-grained scoring are optimized with text classification and sequence labeling pipeline, respectively. With the introduction of PLMs, the dependence on labeled training data has been greatly reduced, and performance has improved., Comment: Under Review, ICASSP 2023

The vapor-liquid-solid (VLS) method is considered a plausible technique for synthesizing germanium (Ge) nanostructures (e.g. nanowires), which have a broad range of applications due to their unique electronic properties and intrinsic compatibility with silicon. However, crystallization failures and material defects are still frequently observed in VLS processes, with insufficient understanding of their underlying mechanisms due to instrumental limitations for high-resolution in-situ characterizations. Employing an accurate interatomic potential well fitted to the gold-germanium (Au-Ge) phase diagram, we performed molecular dynamics simulations for a systematic investigation on the Au-catalyzed growth process of Ge crystals. From the simulations, relationships were established between the overall Ge growth rate and several main synthesis conditions, including substrate crystallographic orientation, temperature and Ge supersaturation in liquid. The dynamical behaviors of Ge atoms near the liquid-solid growing interface were captured, from which the atom surface stability and exchange rate were estimated for quantifying the atomistic details of the growth. These interface properties were further linked to the surface morphologies, to explain the observed orientation-dependent growing modes. This study sheds new lights into the understanding of the VLS growth mechanisms of Ge crystals, and provides scientific guidelines for designing innovative synthesis methods for similar nanomaterials.

Motivated by civic problems such as participatory budgeting and multiwinner elections, we consider the problem of public good allocation: Given a set of indivisible projects (or candidates) of different sizes, and voters with different monotone utility functions over subsets of these candidates, the goal is to choose a budget-constrained subset of these candidates (or a committee) that provides fair utility to the voters. The notion of fairness we adopt is that of core stability from cooperative game theory: No subset of voters should be able to choose another blocking committee of proportionally smaller size that provides strictly larger utility to all voters that deviate. The core provides a strong notion of fairness, subsuming other notions that have been widely studied in computational social choice. It is well-known that an exact core need not exist even when utility functions of the voters are additive across candidates. We therefore relax the problem to allow approximation: Voters can only deviate to the blocking committee if after they choose any extra candidate (called an additament), their utility still increases by an $\alpha$ factor. If no blocking committee exists under this definition, we call this an $\alpha$-core. Our main result is that an $\alpha$-core, for $\alpha < 67.37$, always exists when utilities of the voters are arbitrary monotone submodular functions, and this can be computed in polynomial time. This result improves to $\alpha < 9.27$ for additive utilities, albeit without the polynomial time guarantee. Our results are a significant improvement over prior work that only shows logarithmic approximations for the case of additive utilities. We complement our results with a lower bound of $\alpha > 1.015$ for submodular utilities, and a lower bound of any function in the number of voters and candidates for general monotone utilities., Comment: Accepted by ACM-SIAM Symposium on Discrete Algorithms (SODA 2022)

Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless, with the fixed size of patches in ViT, the class token in deep layer focuses on the global receptive field and cannot generate multi-granularity features for FGVR. To capture region attention without box annotations and compensate for ViT shortcomings in FGVR, we propose a novel method named Adaptive attention multi-scale Fusion Transformer (AFTrans). The Selective Attention Collection Module (SACM) in our approach leverages attention weights in ViT and filters them adaptively to correspond with the relative importance of input patches. The multiple scales (global and local) pipeline is supervised by our weights sharing encoder and can be easily trained end-to-end. Comprehensive experiments demonstrate that AFTrans can achieve SOTA performance on three published fine-grained benchmarks: CUB-200-2011, Stanford Dogs and iNat2017.