arXiv subjects

Chong Wang

Publications and source records attributed to Chong Wang.

At least 235 records · Page 13Linked to original sources

arXiv2022

DPAUC: Differentially Private AUC Computation in Federated Learning

Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. The prior work on FL has mostly studied how to protect label privacy during model training. However, model evaluation in FL might also lead to potential leakage of private label information. In this work, we propose an evaluation algorithm that can accurately compute the widely used AUC (area under the curve) metric when using the label differential privacy (DP) in FL. Through extensive experiments, we show our algorithms can compute accurate AUCs compared to the ground truth. The code is available at {\url{https://github.com/bytedance/fedlearner/tree/master/example/privacy/DPAUC}}.

cs.LG↗

arXiv2022

Learning Regularized Positional Encoding for Molecular Prediction

Machine learning has become a promising approach for molecular modeling. Positional quantities, such as interatomic distances and bond angles, play a crucial role in molecule physics. The existing works rely on careful manual design of their representation. To model the complex nonlinearity in predicting molecular properties in an more end-to-end approach, we propose to encode the positional quantities with a learnable embedding that is continuous and differentiable. A regularization technique is employed to encourage embedding smoothness along the physical dimension. We experiment with a variety of molecular property and force field prediction tasks. Improved performance is observed for three different model architectures after plugging in the proposed positional encoding method. In addition, the learned positional encoding allows easier physics-based interpretation. We observe that tasks of similar physics have the similar learned positional encoding.

cs.LG↗

arXiv2022

Supervised Pretraining for Molecular Force Fields and Properties Prediction

Machine learning approaches have become popular for molecular modeling tasks, including molecular force fields and properties prediction. Traditional supervised learning methods suffer from scarcity of labeled data for particular tasks, motivating the use of large-scale dataset for other relevant tasks. We propose to pretrain neural networks on a dataset of 86 millions of molecules with atom charges and 3D geometries as inputs and molecular energies as labels. Experiments show that, compared to training from scratch, fine-tuning the pretrained model can significantly improve the performance for seven molecular property prediction tasks and two force field tasks. We also demonstrate that the learned representations from the pretrained model contain adequate information about molecular structures, by showing that linear probing of the representations can predict many molecular information including atom types, interatomic distances, class of molecular scaffolds, and existence of molecular fragments. Our results show that supervised pretraining is a promising research direction in molecular modeling

physics.chem-ph↗

arXiv2022

Counterfactually Evaluating Explanations in Recommender Systems

Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a significant challenge for researchers and practitioners. Prior work mainly conducts human study to evaluate explanation quality, which is usually expensive, time-consuming, and prone to human bias. In this paper, we propose an offline evaluation method that can be computed without human involvement. To evaluate an explanation, our method quantifies its counterfactual impact on the recommendation. To validate the effectiveness of our method, we carry out an online user study. We show that, compared to conventional methods, our method can produce evaluation scores more correlated with the real human judgments, and therefore can serve as a better proxy for human evaluation. In addition, we show that explanations with high evaluation scores are considered better by humans. Our findings highlight the promising direction of using the counterfactual approach as one possible way to evaluate recommendation explanations.

cs.AI↗

arXiv2022

Dynamical criticality of spin-shear coupling in van der Waals antiferromagnets

The interplay between a multitude of electronic, spin, and lattice degrees of freedom underlies the complex phase diagrams of quantum materials. Layer stacking in van der Waals (vdW) heterostructures is responsible for exotic electronic and magnetic properties, which inspires stacking control of two-dimensional magnetism. Beyond the interplay between stacking order and interlayer magnetism, we discover a spin-shear coupling mechanism in which a subtle shear of the atomic layers can have a profound effect on the intralayer magnetic order in a family of vdW antiferromagnets. Using time-resolved x-ray diffraction and optical linear dichroism measurements, interlayer shear is identified as the primary structural degree of freedom that couples with magnetic order. The recovery times of both shear and magnetic order upon optical excitation diverge at the magnetic ordering temperature with the same critical exponent. The time-dependent Ginzburg-Landau theory shows that this concurrent critical slowing down arises from a linear coupling of the interlayer shear to the magnetic order, which is dictated by the broken mirror symmetry intrinsic to the monoclinic stacking. Our results highlight the importance of interlayer shear in ultrafast control of magnetic order via spin-mechanical coupling.

cond-mat.mtrl-sci↗

arXiv2022

The Role of User Reviews in App Updates: A Preliminary Investigation on App Release Notes

Release planning for mobile apps has recently become an area of active research. Prior research in this area concentrated on the analysis of release notes and on tracking user reviews to support app evolution with issue trackers. However, little is known about the impact of user reviews on the evolution of mobile apps. Our work explores the role of user reviews in app updates based on release notes. For this purpose, we collected user reviews and release notes of Spotify, the 'number one' app in the 'Music' category in Apple App Store, as the research data. Then, we manually removed non-informative parts of each release note, and manually determined the relevance of the app reviews with respect to the release notes. We did this by using Word2Vec calculation techniques based on the top 80 app release notes with the highest similarities. Our empirical results show that more than 60% of the matched reviews are actually irrelevant to the corresponding release notes. When zooming in at these relevant user reviews, we found that around half of them were posted before the new release and referred to requests, suggestions, and complaints. Whereas, the other half of the relevant user reviews were posted after updating the apps and concentrated more on bug reports and praise.

cs.SE↗

arXiv2022

Dynamical Effects from Anomaly: Modified Electrodynamics in Weyl Semimetal

We discuss the modified quantum electrodynamics from a time-reversal-breaking Weyl semimetal coupled with a $U(1)$ gauge (electromagnetic) field. A key role is played by the soft dispersion of the photons in a particular direction, say $\hat{z}$, due to the Hall conductivity of the Weyl semimetal. Due to the soft photon, the fermion velocity in $\hat{z}$ is logarithmically reduced under renormalization group flow, together with the fine structure constant. Meanwhile, fermions acquire a finite lifetime from spontaneous emission of the soft photon, namely the Cherenkov radiation. At low energy $E$, the inverse of the fermion lifetime scales as $τ^{-1}\sim E/{\rm PolyLog}(E)$. Therefore, even though fermion quasiparticles are eventually well-defined at very low energy, over a wide intermediate energy window the Weyl semimetal behaves like a marginal Fermi liquid. Phenomenologically, our results are more relevant for emergent Weyl semimetals, where the fermions and photons all emerge from strongly correlated lattice systems. Possible experimental implications are discussed.

cond-mat.str-el↗

arXiv2022

Topological characterization of Lieb-Schultz-Mattis constraints and applications to symmetry-enriched quantum criticality

Lieb-Schultz-Mattis (LSM) theorems provide powerful constraints on the emergibility problem, i.e. whether a quantum phase or phase transition can emerge in a many-body system. We derive the topological partition functions that characterize the LSM constraints in spin systems with $G_s\times G_{int}$ symmetry, where $G_s$ is an arbitrary space group in one or two spatial dimensions, and $G_{int}$ is any internal symmetry whose projective representations are classified by $\mathbb{Z}_2^k$ with $k$ an integer. We then apply these results to study the emergibility of a class of exotic quantum critical states, including the well-known deconfined quantum critical point (DQCP), $U(1)$ Dirac spin liquid (DSL), and the recently proposed non-Lagrangian Stiefel liquid. These states can emerge as a consequence of the competition between a magnetic state and a non-magnetic state. We identify all possible realizations of these states on systems with $SO(3)\times \mathbb{Z}_2^T$ internal symmetry and either $p6m$ or $p4m$ lattice symmetry. Many interesting examples are discovered, including a DQCP adjacent to a ferromagnet, stable DSLs on square and honeycomb lattices, and a class of quantum critical spin-quadrupolar liquids of which the most relevant spinful fluctuations carry spin-$2$. In particular, there is a realization of spin-quadrupolar DSL that is beyond the usual parton construction. We further use our formalism to analyze the stability of these states under symmetry-breaking perturbations, such as spin-orbit coupling. As a concrete example, we find that a DSL can be stable in a recently proposed candidate material, NaYbO$_2$.

cond-mat.str-el↗

arXiv2022

Theory and Experiments of Pressure-Tunable Broadband Light Emission from Self-Trapped Excitons in Metal Halide Crystals

Hydrostatic pressure has been commonly applied to tune broadband light emissions from self-trapped excitons (STE) in perovskites for producing white light and study of basic electron-phonon interactions. However, a general theory is still lacking to understand pressure-driven evolution of STE emissions. In this work we first identify a theoretical model that predicts the effect of hydrostatic pressure on STE emission spectrum, we then report the observation of extremely broadband photoluminescence emission and its wide pressure spectral tuning in 2D indirect bandgap CsPb2Br5 crystals. An excellent agreement is found between the theory and experiment on the peculiar experimental observation of STE emission with a nearly constant spectral bandwidth but linearly increasing energy with pressure below 2 GPa. Further analysis by the theory and experiment under higher pressure reveals that two types of STE are involved and respond differently to external pressure. We subsequently survey published STE emissions and discovered that most of them show a spectral blue-shift under pressure, as predicted by the theory. The identification of an appropriate theoretical model and its application to STE emission through the coordinate configuration diagram paves the way for engineering the STE emission and basic understanding of electron-phonon interaction.

cond-mat.mtrl-sci↗

arXiv2022

Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation

When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views. These multiple related images provide complementary diagnostic information and can improve the radiologist's classification accuracy. Unfortunately, most existing deep learning systems, trained with globally-labelled images, lack the ability to jointly analyse and integrate global and local information from these multiple views. By ignoring the potentially valuable information present in multiple images of a screening episode, one limits the potential accuracy of these systems. Here, we propose a new multi-view global-local analysis method that mimics the radiologist's reading procedure, based on a global consistency learning and local co-occurrence learning of ipsilateral views in mammograms. Extensive experiments show that our model outperforms competing methods, in terms of classification accuracy and generalisation, on a large-scale private dataset and two publicly available datasets, where models are exclusively trained and tested with global labels.

cs.CV↗

arXiv2022

Collaborative Anomaly Detection

In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item. This can be formulated as an anomaly detection (AD) problem distinguishing between "common users" (nominal) and "fresh users" (anomalous). Considering the sheer volume of items and the sparsity of user-item paired data, independently applying conventional single-task detection methods on each item quickly becomes difficult, while correlations between items are ignored. To address this multi-task anomaly detection problem, we propose collaborative anomaly detection (CAD) to jointly learn all tasks with an embedding encoding correlations among tasks. We explore CAD with conditional density estimation and conditional likelihood ratio estimation. We found that: $i$) estimating a likelihood ratio enjoys more efficient learning and yields better results than density estimation. $ii$) It is beneficial to select a small number of tasks in advance to learn a task embedding model, and then use it to warm-start all task embeddings. Consequently, these embeddings can capture correlations between tasks and generalize to new correlated tasks.

cs.LG↗

arXiv2022

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification

Real-world large-scale medical image analysis (MIA) datasets have three challenges: 1) they contain noisy-labelled samples that affect training convergence and generalisation, 2) they usually have an imbalanced distribution of samples per class, and 3) they normally comprise a multi-label problem, where samples can have multiple diagnoses. Current approaches are commonly trained to solve a subset of those problems, but we are unaware of methods that address the three problems simultaneously. In this paper, we propose a new training module called Non-Volatile Unbiased Memory (NVUM), which non-volatility stores running average of model logits for a new regularization loss on noisy multi-label problem. We further unbias the classification prediction in NVUM update for imbalanced learning problem. We run extensive experiments to evaluate NVUM on new benchmarks proposed by this paper, where training is performed on noisy multi-label imbalanced chest X-ray (CXR) training sets, formed by Chest-Xray14 and CheXpert, and the testing is performed on the clean multi-label CXR datasets OpenI and PadChest. Our method outperforms previous state-of-the-art CXR classifiers and previous methods that can deal with noisy labels on all evaluations. Our code is available at https://github.com/FBLADL/NVUM.

cs.CV↗

arXiv2022

REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration

Image restoration schemes based on the pre-trained deep models have received great attention due to their unique flexibility for solving various inverse problems. In particular, the Plug-and-Play (PnP) framework is a popular and powerful tool that can integrate an off-the-shelf deep denoiser for different image restoration tasks with known observation models. However, obtaining the observation model that exactly matches the actual one can be challenging in practice. Thus, the PnP schemes with conventional deep denoisers may fail to generate satisfying results in some real-world image restoration tasks. We argue that the robustness of the PnP framework is largely limited by using the off-the-shelf deep denoisers that are trained by deterministic optimization. To this end, we propose a novel deep reinforcement learning (DRL) based PnP framework, dubbed RePNP, by leveraging a light-weight DRL-based denoiser for robust image restoration tasks. Experimental results demonstrate that the proposed RePNP is robust to the observation model used in the PnP scheme deviating from the actual one. Thus, RePNP can generate more reliable restoration results for image deblurring and super resolution tasks. Compared with several state-of-the-art deep image restoration baselines, RePNP achieves better results subjective to model deviation with fewer model parameters.

eess.IV↗

arXiv2022

Differentially Private Multi-Party Data Release for Linear Regression

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects. However the majority of prior work has focused on scenarios where a single party owns all the data. In this paper we focus on the multi-party setting, where different stakeholders own disjoint sets of attributes belonging to the same group of data subjects. Within the context of linear regression that allow all parties to train models on the complete data without the ability to infer private attributes or identities of individuals, we start with directly applying Gaussian mechanism and show it has the small eigenvalue problem. We further propose our novel method and prove it asymptotically converges to the optimal (non-private) solutions with increasing dataset size. We substantiate the theoretical results through experiments on both artificial and real-world datasets.

cs.CR↗

arXiv2022

Edge physics at the deconfined transition between a quantum spin Hall insulator and a superconductor

We study the edge physics of the deconfined quantum phase transition (DQCP) between a spontaneous quantum spin Hall (QSH) insulator and a spin-singlet superconductor (SC). Although the bulk of this transition is in the same universality class as the paradigmatic deconfined Neel to valence-bond-solid transition, the boundary physics has a richer structure due to proximity to a quantum spin Hall state. We use the parton trick to write down an effective field theory for the QSH-SC transition in the presence of a boundary. We calculate various edge properties in an $N\to\infty$ limit. We show that the boundary Luttinger liquid in the QSH state survives at the phase transition, but only as "fractional" degrees of freedom that carry charge but not spin. The physical fermion remains gapless on the edge at the critical point, with a universal jump in the fermion scaling dimension as the system approaches the transition from the QSH side. The critical point could be viewed as a gapless analogue of the quantum spin Hall state but with the full $SU(2)$ spin rotation symmetry, which cannot be realized if the bulk is gapped.

cond-mat.str-el↗

arXiv2022

Intercell Moiré Exciton Complexes in Electron Lattices

Excitons, Coulomb-bound electron-hole pairs, play a fundamental role in both optical excitation and correlated phenomena in solids. When an exciton interacts with other quasi-particles, few- and many-body excited states, such as trions, exciton Fermi-polarons, Mahan excitons can appear. Here, we report a new interaction between exciton and charges enabled by unusual quantum confinement in 2D moiré superlattices, which results in novel exciton many-body ground states composed of moiré excitons and correlated electron lattices. Unique to H-stacked (or 60o-twisted) WS2/WSe2 heterobilayer, we found that the interlayer atomic registry and moiré structural reconstruction leads to an interlayer moiré exciton (IME) whose hole in one layer is surrounded by its partner electron's wavefunction spread among three adjacent moiré traps in the other layer. This 3D excitonic structure can enable large in-plane electrical quadrupole moments in addition to the vertical dipole. Upon doping, the electric quadrupole facilitates the binding of IME to the charges in neighboring moiré cells, forming an intercell charged exciton complex. The exciton complex is unveiled by the IME photoluminescence energy jumps when the electron lattices form at both fractional and integer-filled moiré minibands, with replica-like spectral features between successive integer moiré fillings. Our work provides the framework in understanding and engineering emergent exciton many-body states in correlated moiré charge orders.

cond-mat.mes-hall↗

arXiv2022

Linear Complexity Randomized Self-attention Mechanism

Recently, random feature attentions (RFAs) are proposed to approximate the softmax attention in linear time and space complexity by linearizing the exponential kernel. In this paper, we first propose a novel perspective to understand the bias in such approximation by recasting RFAs as self-normalized importance samplers. This perspective further sheds light on an \emph{unbiased} estimator for the whole softmax attention, called randomized attention (RA). RA constructs positive random features via query-specific distributions and enjoys greatly improved approximation fidelity, albeit exhibiting quadratic complexity. By combining the expressiveness in RA and the efficiency in RFA, we develop a novel linear complexity self-attention mechanism called linear randomized attention (LARA). Extensive experiments across various domains demonstrate that RA and LARA significantly improve the performance of RFAs by a substantial margin.

cs.LG↗

arXiv2022

Gate-tunable proximity effects in graphene on layered magnetic insulators

The extreme versatility of two-dimensional van der Waals (vdW) materials derives from their ability to exhibit new electronic properties when assembled in proximity with dissimilar crystals. For example, although graphene is inherently non-magnetic, recent work has reported a magnetic proximity effect in graphene interfaced with magnetic substrates, potentially enabling a pathway towards achieving a high-temperature quantum anomalous Hall effect. Here, we investigate heterostructures of graphene and chromium trihalide magnetic insulators (CrI$_3$, CrBr$_3$, and CrCl$_3$). Surprisingly, we are unable to detect a magnetic exchange field in the graphene, but instead discover proximity effects featuring unprecedented gate-tunability. The graphene becomes highly hole-doped due to charge transfer from the neighboring magnetic insulator, and further exhibits a variety of atypical transport features. These include highly extended quantum Hall plateaus, abrupt reversals in the Landau level filling sequence, and hysteresis over at least days-long time scales. In the case of CrI$_3$, we are able to completely suppress the charge transfer and all attendant atypical transport effects by gating. The charge transfer can additionally be altered in a first-order phase transition upon switching the magnetic states of the nearest CrI$_3$ layers. Our results provide a roadmap for exploiting the magnetic proximity effect in graphene, and motivate further experiments with other magnetic insulators.

cond-mat.mes-hall↗