arXiv subjects

Yu Yang

Publications and source records attributed to Yu Yang.

At least 181 records · Page 10Linked to original sources

arXiv2024

Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias

Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In this work, we provide the first theoretical analysis of the effect of simplicity bias on learning spurious correlations. Notably, we show that examples with spurious features are provably separable based on the model's output early in training. We further illustrate that if spurious features have a small enough noise-to-signal ratio, the network's output on the majority of examples is almost exclusively determined by the spurious features, leading to poor worst-group test accuracy. Finally, we propose SPARE, which identifies spurious correlations early in training and utilizes importance sampling to alleviate their effect. Empirically, we demonstrate that SPARE outperforms state-of-the-art methods by up to 21.1% in worst-group accuracy, while being up to 12x faster. We also show that SPARE is a highly effective but lightweight method to discover spurious correlations.

cs.LG↗

arXiv2024

Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation

Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on three real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.

cs.IR↗

arXiv2024

Phonon-lithium ion interactions: A case study of LiM(SeO3)2

Li ion diffusion is fundamentally a thermally activated ion hopping process. Recently, soft lattice, anharmonic phonon and paddlewheel mechanism have been proposed to potentially benefit the ion transport, while the understanding of vibrational couplings of mobile ion and anions is still limited but essential. Herein, we access the ionic conductivity, the stability and the lattice dynamics in LiM(SeO3)2 (M =Al, Ga, In, Sc, Y, and La) with two types of oxygen anions within LiO4 polyhedron, namely edge-shared and corner-shared, the prototype of which, LiGa(SeO3)2, has been experimentally synthesized. We studied in detail the anharmonic and harmonic phonon interactions, as well as couplings between vibrations of edge-bonded or corner-bonded anions in Li polyanions and Li ion diffusion. As M changing from Sc to La, anharmonic phonons increase alongside reduced activation energy for Li diffusion. Phonon modes involving edge-bonded oxygen anions contribute more to Li migration than corner-bonded oxygen anions, owing to greater atomic interactions between Li ions and edge-bonded anions. Thus, rather than the overall lattice softness, attentions shall be paid to reduce the frequency of the critical phonons contributing to Li ion diffusions as well as to increase the anharmonicity, for the design of Li ion superionic conductors for all-solid-state-batteries.

cond-mat.mtrl-sci↗

arXiv2024

Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach

In the era of modern education, addressing cross-school learner diversity is crucial, especially in personalized recommender systems for elective course selection. However, privacy concerns often limit cross-school data sharing, which hinders existing methods' ability to model sparse data and address heterogeneity effectively, ultimately leading to suboptimal recommendations. In response, we propose HFRec, a heterogeneity-aware hybrid federated recommender system designed for cross-school elective course recommendations. The proposed model constructs heterogeneous graphs for each school, incorporating various interactions and historical behaviors between students to integrate context and content information. We design an attention mechanism to capture heterogeneity-aware representations. Moreover, under a federated scheme, we train individual school-based models with adaptive learning settings to recommend tailored electives. Our HFRec model demonstrates its effectiveness in providing personalized elective recommendations while maintaining privacy, as it outperforms state-of-the-art models on both open-source and real-world datasets.

cs.IR↗

arXiv2024

Quantum multiparameter estimation enhanced by a topological phase transition

In quantum multiparameter estimation, multiple to-be-estimated parameters are encoded in a quantum dynamics system by a unitary evolution. As the parameters vary, the system may undergo a topological phase transition (TPT). In this paper, we investigate two SU(2) TPT models and propose the singular behavior of the quantum metric tensor around the TPT point as a tool for the simultaneous optimal estimation of multiple parameters. We find that the proposed TPT sensing protocol can achieve the same metrology performance as the quantum-control-enhanced one. Moreover, the probe state of the TPT sensing protocol is only the ground state of the Hamiltonian rather than the entangled state required in the control-enhanced one. In addition, an adaptive multiparameter estimation strategy is developed for updating the estimated values until the desired quantum Cramér-Rao bound is approached. Our work reinforces the connection between quantum multiparameter estimation and topology physics, with potential inspiration for quantum critical metrology.

quant-ph↗

arXiv2024

Shell effects on the drift and fluctuation in multinucleon transfer reactions

This study employs the dinuclear system model (DNS-sysu) to investigate drift and fluctuation mechanisms in 136Xe + 209Bi collisions above the Coulomb barrier. The DNS-sysu model demonstrated its effectiveness in providing reasonable descriptions of drift and fluctuation dynamics for the multinucleon transfer reaction at low energies. We observe temperature-induced changes in the shell effect, impacting nucleon transfer. At higher energies, the weakening constraint of the potential energy surface leads to a reversal in the evolution direction. Additionally, the consideration of shell corrections notably affects fragment distribution at low energies but diminishes for high-energy conditions. This research provides valuable insights into understanding the macroscopic manifestation of nucleon transfer in the multinucleon transfer reaction.

nucl-th↗

arXiv2023

Quantum squeezing in a nonlinear mechanical oscillator

Mechanical degrees of freedom are natural candidates for continuous-variable quantum information processing and bosonic quantum simulations. These applications, however, require the engineering of squeezing and nonlinearities in the quantum regime. Here we demonstrate ground state squeezing of a gigahertz-frequency mechanical resonator coupled to a superconducting qubit. This is achieved by parametrically driving the qubit, which results in an effective two-phonon drive. In addition, we show that the resonator mode inherits a nonlinearity from the off-resonant coupling with the qubit, which can be tuned by controlling the detuning. We thus realize a mechanical squeezed Kerr oscillator, where we demonstrate the preparation of non-Gaussian quantum states of motion with Wigner function negativities and high quantum Fisher information. This shows that our results also have applications in quantum metrology and sensing.

quant-ph↗

arXiv2023

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models. Current models often generate monotonous and simplistic dance sequences that misalign with human preferences because they lack exploration capabilities. The E3D2 framework involves a reward model trained from automatically-ranked dance demonstrations, which then guides the reinforcement learning process. This approach encourages the agent to explore and generate high quality and diverse dance movement sequences. The soundness of the reward model is both theoretically and experimentally validated. Empirical experiments demonstrate the effectiveness of E3D2 on the AIST++ dataset. Project Page: https://sites.google.com/view/e3d2.

cs.HC↗

arXiv2023

Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data

Code datasets, often collected from diverse and uncontrolled sources such as GitHub, potentially suffer from quality issues, thereby affecting the performance and training efficiency of Large Language Models (LLMs) optimized for code generation. Previous studies demonstrated the benefit of using embedding spaces for data pruning, but they mainly focused on duplicate removal or increasing variety, and in other modalities, such as images. Our work focuses on using embeddings to identify and remove "low-quality" code data. First, we explore features of "low-quality" code in embedding space, through the use of synthetic corruptions. Armed with this knowledge, we devise novel pruning metrics that operate in embedding space to identify and remove low-quality entries in the Stack dataset. We demonstrate the benefits of this synthetic corruption informed pruning (SCIP) approach on the well-established HumanEval and MBPP benchmarks, outperforming existing embedding-based methods. Importantly, we achieve up to a 3% performance improvement over no pruning, thereby showing the promise of insights from synthetic corruptions for data pruning.

cs.CL↗

arXiv2023

Constraining the Woods-Saxon potential in fusion reactions based on the neural network

The accurate determination of the nuclear interaction potential is essential for predicting the fusion cross sections and understanding the reaction mechanism, which plays an important role in the synthesis of superheavy elements. In this work, the neural network, which combines with the calculations of the fusion cross sections via the Hill-Wheeler formula, is developed to optimize the parameters of the Woods-Saxon potential by comparing the experimental values. The correlations between the parameters of Woods-Saxon potential and the reaction partners, which can be quantitatively fitted to a sigmoid-like function with the mass numbers, have been displayed manifestly for the first time. This study could promote the accurate estimation of nucleus-nucleus interaction potential in low energy heavy-ion collisions.

nucl-th↗

arXiv2023

Role of the isospin diffusion on cluster transfer in $^{12,14}$C + $^{209}$Bi reactions

Heavy-ion collisions at near-barrier energies provide a crucial pathway for investigating nucleon correlations and clustering structures. Recent experimental results showed that the valence neutrons in light projectiles obviously enhance the $α$ transfer. This finding is extremely puzzled and fascinating, because it violates the ground-state $Q$ value systematics unexpectedly. In this work, the time-dependent Hartree-Fock approach is utilized to investigate the cluster transfer. By comparing the reactions $^{12,14}$C + $^{209}$Bi, we discover that above puzzling behavior is because of the strong correlation between isospin diffusion and clustering. Our calculations clearly show that the equilibrium of neutron-to-proton ratio strongly inhibits the clustering. This work opens a prospect for investigating the clustering in open quantum system.

nucl-th↗

arXiv2023

Training A Multi-stage Deep Classifier with Feedback Signals

Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons. The classifiers of a multi-stage process are usually Neural Network (NN) models trained independently or in their inference order without considering the signals from the latter stages. Aimed at two-stage binary classification process, the most common type of MSC, we propose a novel training framework, named Feedback Training. The classifiers are trained in an order reverse to their actual working order, and the classifier at the later stage is used to guide the training of initial-stage classifier via a sample weighting method. We experimentally show the efficacy of our proposed approach, and its great superiority under the scenario of few-shot training.

cs.LG↗

arXiv2023

Bayes-enhanced Multi-view Attention Networks for Robust POI Recommendation

POI recommendation is practically important to facilitate various Location-Based Social Network services, and has attracted rising research attention recently. Existing works generally assume the available POI check-ins reported by users are the ground-truth depiction of user behaviors. However, in real application scenarios, the check-in data can be rather unreliable due to both subjective and objective causes including positioning error and user privacy concerns, leading to significant negative impacts on the performance of the POI recommendation. To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of the user check-ins, and proposes a Bayes-enhanced Multi-view Attention Network. Specifically, we construct personal POI transition graph, the semantic-based POI graph and distance-based POI graph to comprehensively model the dependencies among the POIs. As the personal POI transition graph is usually sparse and sensitive to noise, we design a Bayes-enhanced spatial dependency learning module for data augmentation from the local view. A Bayesian posterior guided graph augmentation approach is adopted to generate a new graph with collaborative signals to increase the data diversity. Then both the original and the augmented graphs are used for POI representation learning to counteract the data uncertainty issue. Next, the POI representations of the three view graphs are input into the proposed multi-view attention-based user preference learning module. By incorporating the semantic and distance correlations of POIs, the user preference can be effectively refined and finally robust recommendation results are achieved. The results of extensive experiments show that BayMAN significantly outperforms the state-of-the-art methods in POI recommendation when the available check-ins are incomplete and noisy.

cs.IR↗

arXiv2023

Boosting Summarization with Normalizing Flows and Aggressive Training

This paper presents FlowSUM, a normalizing flows-based variational encoder-decoder framework for Transformer-based summarization. Our approach tackles two primary challenges in variational summarization: insufficient semantic information in latent representations and posterior collapse during training. To address these challenges, we employ normalizing flows to enable flexible latent posterior modeling, and we propose a controlled alternate aggressive training (CAAT) strategy with an improved gate mechanism. Experimental results show that FlowSUM significantly enhances the quality of generated summaries and unleashes the potential for knowledge distillation with minimal impact on inference time. Furthermore, we investigate the issue of posterior collapse in normalizing flows and analyze how the summary quality is affected by the training strategy, gate initialization, and the type and number of normalizing flows used, offering valuable insights for future research.

cs.CL↗

arXiv2023

Robust Learning with Progressive Data Expansion Against Spurious Correlation

While deep learning models have shown remarkable performance in various tasks, they are susceptible to learning non-generalizable spurious features rather than the core features that are genuinely correlated to the true label. In this paper, beyond existing analyses of linear models, we theoretically examine the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features. Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process. In light of this, we propose a new training algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance. PDE begins with a group-balanced subset of training data and progressively expands it to facilitate the learning of the core features. Experiments on synthetic and real-world benchmark datasets confirm the superior performance of our method on models such as ResNets and Transformers. On average, our method achieves a 2.8% improvement in worst-group accuracy compared with the state-of-the-art method, while enjoying up to 10x faster training efficiency. Codes are available at https://github.com/uclaml/PDE.

cs.LG↗

arXiv2023

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset. However, current dataset distillation techniques fall short, showing a notable performance gap when compared to training on the original data. In this work, we are the first to argue that using just one synthetic subset for distillation will not yield optimal generalization performance. This is because the training dynamics of deep networks drastically change during the training. Hence, multiple synthetic subsets are required to capture the training dynamics at different phases of training. To address this issue, we propose Progressive Dataset Distillation (PDD). PDD synthesizes multiple small sets of synthetic images, each conditioned on the previous sets, and trains the model on the cumulative union of these subsets without requiring additional training time. Our extensive experiments show that PDD can effectively improve the performance of existing dataset distillation methods by up to 4.3%. In addition, our method for the first time enable generating considerably larger synthetic datasets.

cs.CV↗

arXiv2023

ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation

Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise. However, without human annotations, they are typically prone to produce foreground and background layers with non-negligible semantic and visual confusion, dubbed "information leakage", resulting in notable degeneration of the generated segmentation mask. To alleviate this issue, we propose a simple-yet-effective explicit layer independence modeling approach, termed Independent Layer Synthesis GAN (ILSGAN), pursuing independent foreground-background layer generation by encouraging their discrepancy. Specifically, it targets minimizing the mutual information between visible and invisible regions of the foreground and background to spur interlayer independence. Through in-depth theoretical and experimental analyses, we justify that explicit layer independence modeling is critical to suppressing information leakage and contributes to impressive segmentation performance gains. Also, our ILSGAN achieves strong state-of-the-art generation quality and segmentation performance on complex real-world data. Code is available at: https://github.com/qrzou/ILSGAN

cs.CV↗

arXiv2023

Non-Uniform Sampling Reconstruction for Symmetrical NMR Spectroscopy by Exploiting Inherent Symmetry

Symmetrical NMR spectroscopy constitutes a vital branch of multidimensional NMR spectroscopy, providing a powerful tool for the structural elucidation of biological macromolecules. Non-Uniform Sampling (NUS) serves as an effective strategy for averting the prohibitive acquisition time of multidimensional NMR spectroscopy by only sampling a few points according to NUS sampling schedules and reconstructing missing points via algorithms. However, current sampling schedules are unable to maintain the accurate recovery of cross peaks that are weak but important. In this work, we propose a novel sampling schedule termed as SCPG (Symmetrical Copy Poisson Gap) and employ CS (Compressed Sensing) methods for reconstruction. We theoretically prove that the symmetrical constraint, apart from sparsity, is implicitly implemented when SCPG is combined with CS methods. The simulated and experimental data substantiate the advantage of SCPG over state-of-the-art 2D Woven PG in the NUS reconstruction of symmetrical NMR spectroscopy.

eess.SP↗