arXiv subjects

Rui Hou

Publications and source records attributed to Rui Hou.

At least 55 records · Page 3Linked to original sources

arXiv2023

Query Rewriting for Effective Misinformation Discovery

We propose a novel system to help fact-checkers formulate search queries for known misinformation claims and effectively search across multiple social media platforms. We introduce an adaptable rewriting strategy, where editing actions for queries containing claims (e.g., swap a word with its synonym; change verb tense into present simple) are automatically learned through offline reinforcement learning. Our model uses a decision transformer to learn a sequence of editing actions that maximizes query retrieval metrics such as mean average precision. We conduct a series of experiments showing that our query rewriting system achieves a relative increase in the effectiveness of the queries of up to 42%, while producing editing action sequences that are human interpretable.

cs.CL↗

arXiv2023

Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification

Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous works have made remarkable progress in leveraging attention mechanism to extract opinion words for different aspects. However, a persistent challenge is the effective management of semantic mismatches, which stem from attention mechanisms that fall short in adequately aligning opinions words with their corresponding aspect in multi-aspect sentences. To address this issue, we propose a novel Aspect-oriented Opinion Alignment Network (AOAN) to capture the contextual association between opinion words and the corresponding aspect. Specifically, we first introduce a neighboring span enhanced module which highlights various compositions of neighboring words and given aspects. In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect. Extensive experiments on three benchmark datasets demonstrate that our model achieves state-of-the-art results. The source code is available at https://github.com/AONE-NLP/ABSA-AOAN.

cs.CL↗

arXiv2023

Raman and IR spectra of water under graphene nanoconfinement at ambient and extreme pressure-temperature conditions: a first-principles study

The nanoconfinement of water can result in dramatic differences in its physical and chemical properties compared to bulk water. However, a detailed molecular-level understanding of these properties is still lacking. Vibrational spectroscopy, such as Raman and infrared, is a popular experimental tool for studying the structure and dynamics of water, and is often complemented by atomistic simulations to interpret experimental spectra, but there have been few theoretical spectroscopy studies of nanoconfined water using first-principles methods at ambient conditions, let alone under extreme pressure-temperature conditions. Here, we computed the Raman and IR spectra of water nanoconfined by graphene at ambient and extreme pressure-temperature conditions using ab intio simulations. Our results revealed alterations in the Raman stretching and low-frequency bands due to the graphene confinement. We also found spectroscopic evidence indicating that nanoconfinement considerably changes the tetrahedral hydrogen bond network, which is typically found in bulk water. Furthermore, we observed an unusual bending band in the Raman spectrum at ~10 GPa and 1000 K, which is attributed to the unique molecular structure of confined ionic water. Additionally, we found that at ~20 GPa and 1000 K, confined water transformed into a superionic fluid, making it challenging to identify the IR stretching band. Finally, we computed the ionic conductivity of confined water in the ionic and superionic phases. Our results highlight the efficacy of Raman and IR spectroscopy in studying the structure and dynamics of nanoconfined water in a large pressure-temperature range. Our predicted Raman and IR spectra can serve as a valuable guide for future experiments.

cond-mat.mtrl-sci↗

arXiv2023

Llama 2: Open Foundation and Fine-Tuned Chat Models

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.

cs.CL↗

arXiv2023

A Study on Knowledge Distillation from Weak Teacher for Scaling Up Pre-trained Language Models

Distillation from Weak Teacher (DWT) is a method of transferring knowledge from a smaller, weaker teacher model to a larger student model to improve its performance. Previous studies have shown that DWT can be effective in the vision domain and natural language processing (NLP) pre-training stage. Specifically, DWT shows promise in practical scenarios, such as enhancing new generation or larger models using pre-trained yet older or smaller models and lacking a resource budget. However, the optimal conditions for using DWT have yet to be fully investigated in NLP pre-training. Therefore, this study examines three key factors to optimize DWT, distinct from those used in the vision domain or traditional knowledge distillation. These factors are: (i) the impact of teacher model quality on DWT effectiveness, (ii) guidelines for adjusting the weighting value for DWT loss, and (iii) the impact of parameter remapping as a student model initialization technique for DWT.

cs.CL↗

arXiv2023

Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization

Prompt tuning is one of the successful approaches for parameter-efficient tuning of pre-trained language models. Despite being arguably the most parameter-efficient (tuned soft prompts constitute <0.1% of total parameters), it typically performs worse than other efficient tuning methods and is quite sensitive to hyper-parameters. In this work, we introduce Residual Prompt Tuning - a simple and efficient method that significantly improves the performance and stability of prompt tuning. We propose to reparameterize soft prompt embeddings using a shallow network with a residual connection. Our experiments show that Residual Prompt Tuning significantly outperforms prompt tuning on SuperGLUE benchmark. Notably, our method reaches +7 points improvement over prompt tuning with T5-Base and allows to reduce the prompt length by 10x without hurting performance. In addition, we show that our approach is robust to the choice of learning rate and prompt initialization, and is effective in few-shot settings.

cs.CL↗

arXiv2023

MMViT: Multiscale Multiview Vision Transformers

We present Multiscale Multiview Vision Transformers (MMViT), which introduces multiscale feature maps and multiview encodings to transformer models. Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel. At each scale stage, we use a cross-attention block to fuse information across different views. This enables the MMViT model to acquire complex high-dimensional representations of the input at different resolutions. The proposed model can serve as a backbone model in multiple domains. We demonstrate the effectiveness of MMViT on audio and image classification tasks, achieving state-of-the-art results.

cs.CV↗

arXiv2023

SVT: Supertoken Video Transformer for Efficient Video Understanding

Whether by processing videos with fixed resolution from start to end or incorporating pooling and down-scaling strategies, existing video transformers process the whole video content throughout the network without specially handling the large portions of redundant information. In this paper, we present a Supertoken Video Transformer (SVT) that incorporates a Semantic Pooling Module (SPM) to aggregate latent representations along the depth of visual transformer based on their semantics, and thus, reduces redundancy inherent in video inputs.~Qualitative results show that our method can effectively reduce redundancy by merging latent representations with similar semantics and thus increase the proportion of salient information for downstream tasks.~Quantitatively, our method improves the performance of both ViT and MViT while requiring significantly less computations on the Kinectics and Something-Something-V2 benchmarks.~More specifically, with our SPM, we improve the accuracy of MAE-pretrained ViT-B and ViT-L by 1.5% with 33% less GFLOPs and by 0.2% with 55% less FLOPs, respectively, on the Kinectics-400 benchmark, and improve the accuracy of MViTv2-B by 0.2% and 0.3% with 22% less GFLOPs on Kinectics-400 and Something-Something-V2, respectively.

cs.CV↗

arXiv2023

Progressive Prompts: Continual Learning for Language Models

We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a large number of task-specific parameters. Progressive Prompts learns a new soft prompt for each task and sequentially concatenates it with the previously learned prompts, while keeping the base model frozen. Experiments on standard continual learning benchmarks show that our approach outperforms state-of-the-art methods, with an improvement >20% in average test accuracy over the previous best-preforming method on T5 model. We also explore a more challenging continual learning setup with longer sequences of tasks and show that Progressive Prompts significantly outperforms prior methods.

cs.CL↗

arXiv2022

TensorFHE: Achieving Practical Computation on Encrypted Data Using GPGPU

In this paper, we propose TensorFHE, an FHE acceleration solution based on GPGPU for real applications on encrypted data. TensorFHE utilizes Tensor Core Units (TCUs) to boost the computation of Number Theoretic Transform (NTT), which is the part of FHE with highest time-cost. Moreover, TensorFHE focuses on performing as many FHE operations as possible in a certain time period rather than reducing the latency of one operation. Based on such an idea, TensorFHE introduces operation-level batching to fully utilize the data parallelism in GPGPU. We experimentally prove that it is possible to achieve comparable performance with GPGPU as with state-of-the-art ASIC accelerators. TensorFHE performs 913 KOPS and 88 KOPS for NTT and HMULT (key FHE kernels) within NVIDIA A100 GPGPU, which is 2.61x faster than state-of-the-art FHE implementation on GPGPU; Moreover, TensorFHE provides comparable performance to the ASIC FHE accelerators, which makes it even 2.9x faster than the F1+ with a specific workload. Such a pure software acceleration based on commercial hardware with high performance can open up usage of state-of-the-art FHE algorithms for a broad set of applications in real systems.

cs.AR↗

arXiv2022

Uniform Masking Prevails in Vision-Language Pretraining

Masked Language Modeling (MLM) has proven to be an essential component of Vision-Language (VL) pretraining. To implement MLM, the researcher must make two design choices: the masking strategy, which determines which tokens to mask, and the masking rate, which determines how many tokens to mask. Previous work has focused primarily on the masking strategy while setting the masking rate at a default of 15\%. In this paper, we show that increasing this masking rate improves downstream performance while simultaneously reducing performance gap among different masking strategies, rendering the uniform masking strategy competitive to other more complex ones. Surprisingly, we also discover that increasing the masking rate leads to gains in Image-Text Matching (ITM) tasks, suggesting that the role of MLM goes beyond language modeling in VL pretraining.

cs.LG↗

arXiv2022

Remapped Cache Layout: Thwarting Cache-Based Side-Channel Attacks with a Hardware Defense

As cache-based side-channel attacks become serious security problems, various defenses have been proposed and deployed in both software and hardware. Consequently, cache-based side-channel attacks on processes co-residing on the same core are becoming extremely difficult. Most of recent attacks then shift their focus to the last-level cache (LLC). Although cache partitioning is currently the most promising defense against the attacks abusing LLC, it is ineffective in thwarting the side-channel attacks that automatically create eviction sets or bypass the user address space layout randomization. In fact, these attacks are largely undefended in current computer systems. We propose Remapped Cache Layout (\textsf{RCL}) -- a pure hardware defense against a broad range of conflict-based side-channel attacks. \textsf{RCL} obfuscates the mapping from address to cache sets; therefore, an attacker cannot accurately infer the location of her data in caches or using a cache set to infer her victim's data. To our best knowledge, it is the first defense to thwart the aforementioned largely undefended side-channel attacks . \textsf{RCL} has been implemented in a superscalar processor and detailed evaluation results show that \textsf{RCL} incurs only small costs in area, frequency and execution time.

cs.CR↗

arXiv2022

UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning

Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited. However, different PELT methods may perform rather differently on the same task, making it nontrivial to select the most appropriate method for a specific task, especially considering the fast-growing number of new PELT methods and tasks. In light of model diversity and the difficulty of model selection, we propose a unified framework, UniPELT, which incorporates different PELT methods as submodules and learns to activate the ones that best suit the current data or task setup via gating mechanism. On the GLUE benchmark, UniPELT consistently achieves 1~4% gains compared to the best individual PELT method that it incorporates and even outperforms fine-tuning under different setups. Moreover, UniPELT generally surpasses the upper bound that takes the best performance of all its submodules used individually on each task, indicating that a mixture of multiple PELT methods may be inherently more effective than single methods.

cs.CL↗

arXiv2022

Defensive Design of Saturating Counters Based on Differential Privacy

The saturating counter is the basic module of the dynamic branch predictor, which involves the core technique to improve instruction level parallelism performance in modern processors. However, most studies focus on the performance improvement and hardware consumption of saturating counters, while ignoring the security problems they may cause. In this paper, we creatively propose to study and design saturating counters from the defense perspective of differential privacy, so that attackers cannot distinguish the states that saturating counters are in and further infer sensitive information. To obtain theoretical guarantees, we use Markov chain to formalize the attack algorithm applied to the saturating counter, investigate into the optimal attack strategy and calculate the probability of successful attack. Furthermore, we find that the attacker is able to accurately guess the branch execution of the victim's process in the existing saturating counters. To avoid this, we design a new probabilistic saturating counter, which generalizes the existing conventional and probabilistic saturating counters. The guarantee of differential privacy is applied to deduce parameters of the new saturating counters so that the security requirement can be satisfied. We also theoretically calculate the misprediction rate when the saturating counter reaches the steady state. The experimental results on testing programs show that the calculated theoretical results agree with the experimental performances. Compared with the existing conventional and probabilistic saturating counters, when the parameters of our designed models are selected appropriately, the new saturating counters can not only ensure similar operational performance, but also establish strict security guarantee.

cs.CR↗

arXiv2022

IDPG: An Instance-Dependent Prompt Generation Method

Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage. It freezes the pre-trained language model and only optimizes a few task-specific prompts. In this paper, we propose a conditional prompt generation method to generate prompts for each input instance, referred to as the Instance-Dependent Prompt Generation (IDPG). Unlike traditional prompt tuning methods that use a fixed prompt, IDPG introduces a lightweight and trainable component to generate prompts based on each input sentence. Extensive experiments on ten natural language understanding (NLU) tasks show that the proposed strategy consistently outperforms various prompt tuning baselines and is on par with other efficient transfer learning methods such as Compacter while tuning far fewer model parameters.

cs.CL↗

arXiv2021

Classification of Multiple Diseases on Body CT Scans using Weakly Supervised Deep Learning

Purpose: To design multi-disease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports.Materials & Methods: This retrospective study included a total of 12,092 patients (mean age 57 +- 18; 6,172 women) for model development and testing (from 2012-2017). Rule-based algorithms were used to extract 19,225 disease labels from 13,667 body CT scans from 12,092 patients. Using a three-dimensional DenseVNet, three organ systems were segmented: lungs and pleura; liver and gallbladder; and kidneys and ureters. For each organ, a three-dimensional convolutional neural network classified no apparent disease versus four common diseases for a total of 15 different labels across all three models. Testing was performed on a subset of 2,158 CT volumes relative to 2,875 manually derived reference labels from 2133 patients (mean age 58 +- 18;1079 women). Performance was reported as receiver operating characteristic area under the curve (AUC) with 95% confidence intervals by the DeLong method. Results: Manual validation of the extracted labels confirmed 91% to 99% accuracy across the 15 different labels. AUCs for lungs and pleura labels were: atelectasis 0.77 (95% CI: 0.74, 0.81), nodule 0.65 (0.61, 0.69), emphysema 0.89 (0.86, 0.92), effusion 0.97 (0.96, 0.98), and no apparent disease 0.89 (0.87, 0.91). AUCs for liver and gallbladder were: hepatobiliary calcification 0.62 (95% CI: 0.56, 0.67), lesion 0.73 (0.69, 0.77), dilation 0.87 (0.84, 0.90), fatty 0.89 (0.86, 0.92), and no apparent disease 0.82 (0.78, 0.85). AUCs for kidneys and ureters were: stone 0.83 (95% CI: 0.79, 0.87), atrophy 0.92 (0.89, 0.94), lesion 0.68 (0.64, 0.72), cyst 0.70 (0.66, 0.73), and no apparent disease 0.79 (0.75, 0.83). Conclusion: Weakly-supervised deep learning models were able to classify diverse diseases in multiple organ systems.

cs.CV↗

arXiv2021

Ab initio molecular dynamics modelling of organic crystal electro-optical properties

Molecular dynamics calculations were preformed on organic crystals 4-N,N-dimethylamino-4'-N'-methyl-stilbazolium tosylate (DAST) and 4-N,N-dimethylamino-4'-N'-methylstilbazolium 2,4,6-trimethylbenzenesulfonate (DSTMS). Vibrational modes of the structures were investigated to examine the single unit cell phononic contribution of the organic crystals to their terahertz generating capabilities. Linear optical properties were also calculated from snapshots of the molecular dynamics structures through Green-Kubo relations, and compared with experimental transmission.

cond-mat.mtrl-sci↗

arXiv2021

Raman spectra of hydrocarbons under extreme conditions of pressure and temperature: a first-principles study

Hydrocarbons are of great importance in carbon-bearing fluids in deep Earth and in ice giant planets at extreme pressure (P)-temperature (T) conditions. Raman spectroscopy is a powerful tool to study the chemical speciation of hydrocarbons; however, it is challenging to interpret Raman data at extreme conditions. Here, we performed ab initio molecular dynamics simulations coupled with the modern theory of polarization to calculate Raman spectra of methane, ethane, and propane up to 48 GPa and 2000 K. Our method includes anharmonic temperature effects. We studied the pressure and temperature effects on the Raman bands, and identified the characteristic Raman modes for the C-C and C-C-C bonds. Our result may help to interpret in-situ Raman data of hydrocarbons at extreme P-T conditions, with important implications for understanding the deep carbon cycle inside Earth and the compositions of ice giant planets.

physics.comp-ph↗