Search

Stochastic gradient descent with momentum is a popular variant of stochastic gradient descent, which has recently been reported to have a close relationship with the underdamped Langevin diffusion. In this paper, we establish a quantitative error estimate between them in the 1-Wasserstein and total variation distances.

Graph Contrastive Learning (GCL) is a potent paradigm for self-supervised graph learning that has attracted attention across various application scenarios. However, GCL for learning on Text-Attributed Graphs (TAGs) has yet to be explored. Because conventional augmentation techniques like feature embedding masking cannot directly process textual attributes on TAGs. A naive strategy for applying GCL to TAGs is to encode the textual attributes into feature embeddings via a language model and then feed the embeddings into the following GCL module for processing. Such a strategy faces three key challenges: I) failure to avoid information loss, II) semantic loss during the text encoding phase, and III) implicit augmentation constraints that lead to uncontrollable and incomprehensible results. In this paper, we propose a novel GCL framework named LATEX-GCL to utilize Large Language Models (LLMs) to produce textual augmentations and LLMs' powerful natural language processing (NLP) abilities to address the three limitations aforementioned to pave the way for applying GCL to TAG tasks. Extensive experiments on four high-quality TAG datasets illustrate the superiority of the proposed LATEX-GCL method. The source codes and datasets are released to ease the reproducibility, which can be accessed via this link: https://anonymous.4open.science/r/LATEX-GCL-0712.

We study the large N-dimensional limit of the Hessian spectrum at the global minimum of a subclass of spherical mixed p-spin models, extending the relevant results in the regime of topology trivialization.

Timely and effective vulnerability patching is essential for cybersecurity defense, for which various approaches have been proposed yet still struggle to generate valid and correct patches for real-world vulnerabilities. In this paper, we leverage the power and merits of pre-trained large language models (LLMs) to enable automated vulnerability patching using no test input/exploit evidence and without model training/fine-tuning. To elicit LLMs to effectively reason about vulnerable code behaviors, which is essential for quality patch generation, we introduce adaptive prompting on LLMs and instantiate the methodology as LLMPATCH, an automated LLM-based patching system. Our evaluation of LLMPATCH on real-world vulnerable code including zeroday vulnerabilities demonstrates its superior performance to both existing prompting methods and state-of-the-art non-LLM-based techniques (by 98.9% and 65.4% in F1 over the best baseline performance). LLMPATCH has also successfully patched 7 out of 11 zero-day vulnerabilities, including 2 that none of the four baselines compared were able to.

In the rapidly evolving field of natural language processing, dialogue systems primarily employ a single-step dialogue paradigm. Although this paradigm is efficient, it lacks the depth and fluidity of human interactions and does not appear natural. We introduce a novel \textbf{Step}-by-Step Dialogue Paradigm (Stephanie), designed to mimic the ongoing dynamic nature of human conversations. By employing a dual learning strategy and a further-split post-editing method, we generated and utilized a high-quality step-by-step dialogue dataset to fine-tune existing large language models, enabling them to perform step-by-step dialogues. We thoroughly present Stephanie. Tailored automatic and human evaluations are conducted to assess its effectiveness compared to the traditional single-step dialogue paradigm. We will release code, Stephanie datasets, and Stephanie LLMs to facilitate the future of chatbot eras.

Due to the performance degradation of graph neural networks (GNNs) under distribution shifts, the work on out-of-distribution (OOD) generalization on graphs has received widespread attention. A novel perspective involves distinguishing potential confounding biases from different environments through environmental identification, enabling the model to escape environmentally-sensitive correlations and maintain stable performance under distribution shifts. However, in graph data, confounding factors not only affect the generation process of node features but also influence the complex interaction between nodes. We observe that neglecting either aspect of them will lead to a decrease in performance. In this paper, we propose IENE, an OOD generalization method on graphs based on node-level environmental identification and extrapolation techniques. It strengthens the model's ability to extract invariance from two granularities simultaneously, leading to improved generalization. Specifically, to identify invariance in features, we utilize the disentangled information bottleneck framework to achieve mutual promotion between node-level environmental estimation and invariant feature learning. Furthermore, we extrapolate topological environments through graph augmentation techniques to identify structural invariance. We implement the conceptual method with specific algorithms and provide theoretical analysis and proofs for our approach. Extensive experimental evaluations on two synthetic and four real-world OOD datasets validate the superiority of IENE, which outperforms existing techniques and provides a flexible framework for enhancing the generalization of GNNs.

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their counterparts without fine-tuning. However, the comprehensive effects of fine-tuning on the LLMs' generalization ability are not fully understood. This paper delves into the differences between original, unmodified LLMs and their fine-tuned variants. Our primary investigation centers on whether fine-tuning affects the generalization ability intrinsic to LLMs. To elaborate on this, we conduct extensive experiments across five distinct language tasks on various datasets. Our main findings reveal that models fine-tuned on generation and classification tasks exhibit dissimilar behaviors in generalizing to different domains and tasks. Intriguingly, we observe that integrating the in-context learning strategy during fine-tuning on generation tasks can enhance the model's generalization ability. Through this systematic investigation, we aim to contribute valuable insights into the evolving landscape of fine-tuning practices for LLMs., Comment: NAACL 2024

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts., Comment: EMNLP 2024 Main

Hypergraphs provide an effective modeling approach for modeling high-order relationships in many real-world datasets. To capture such complex relationships, several hypergraph neural networks have been proposed for learning hypergraph structure, which propagate information from nodes to hyperedges and then from hyperedges back to nodes. However, most existing methods focus on information propagation between hyperedges and nodes, neglecting the interactions among hyperedges themselves. In this paper, we propose HeIHNN, a hyperedge interaction-aware hypergraph neural network, which captures the interactions among hyperedges during the convolution process and introduce a novel mechanism to enhance information flow between hyperedges and nodes. Specifically, HeIHNN integrates the interactions between hyperedges into the hypergraph convolution by constructing a three-stage information propagation process. After propagating information from nodes to hyperedges, we introduce a hyperedge-level convolution to update the hyperedge embeddings. Finally, the embeddings that capture rich information from the interaction among hyperedges will be utilized to update the node embeddings. Additionally, we introduce a hyperedge outlier removal mechanism in the information propagation stages between nodes and hyperedges, which dynamically adjusts the hypergraph structure using the learned embeddings, effectively removing outliers. Extensive experiments conducted on real-world datasets show the competitive performance of HeIHNN compared with state-of-the-art methods.

Recent studies have shown that attackers can catastrophically reduce the performance of GNNs by maliciously modifying the graph structure or node features on the graph. Adversarial training, which has been shown to be one of the most effective defense mechanisms against adversarial attacks in computer vision, holds great promise for enhancing the robustness of GNNs. There is limited research on defending against attacks by performing adversarial training on graphs, and it is crucial to delve deeper into this approach to optimize its effectiveness. Therefore, based on robust adversarial training on graphs, we propose a hierarchical constraint refinement framework (HC-Ref) that enhances the anti-perturbation capabilities of GNNs and downstream classifiers separately, ultimately leading to improved robustness. We propose corresponding adversarial regularization terms that are conducive to adaptively narrowing the domain gap between the normal part and the perturbation part according to the characteristics of different layers, promoting the smoothness of the predicted distribution of both parts. Moreover, existing research on graph robust adversarial training primarily concentrates on training from the standpoint of node feature perturbations and seldom takes into account alterations in the graph structure. This limitation makes it challenging to prevent attacks based on topological changes in the graph. This paper generates adversarial examples by utilizing graph structure perturbations, offering an effective approach to defend against attack methods that are based on topological changes. Extensive experiments on two real-world graph benchmarks show that HC-Ref successfully resists various attacks and has better node classification performance compared to several baseline methods.

Under certain general conditions, we prove that the stable central limit theorem holds in the total variation distance and get its optimal convergence rate for all $\alpha \in (0,2)$. Our method is by two measure decompositions, one step estimates, and a very delicate induction with respect to $\alpha$. One measure decomposition is light tailed and borrowed from \cite{BC16}, while the other one is heavy tailed and indispensable for lifting convergence rate for small $\alpha$. The proof is elementary and composed of the ingredients at the postgraduate level. Our result clarifies that when $\alpha=1$ and $X$ has a symmetric Pareto distribution, the optimal rate is $n^{-1}$ rather than $n^{-1} (\ln n)^2$ as conjectured in literatures.

We consider locally isotropic Gaussian random fields on the $N$-dimensional Euclidean space for fixed $N$. Using the so called Gaussian Orthogonally Invariant matrices first studied by Mallows in 1961 which include the celebrated Gaussian Orthogonal Ensemble (GOE), we establish the Kac--Rice representation of expected number of critical points of non-isotropic Gaussian fields, complementing the isotropic case obtained by Cheng and Schwartzman in 2018. In the limit $N=\infty$, we show that such a representation can be always given by GOE matrices, as conjectured by Auffinger and Zeng in 2020.

Photon avalanching nanoparticles (ANPs) exhibit extremely nonlinear upconverted emission valuable for sub-diffraction imaging, nanoscale sensing, and optical computing. Avalanching has been demonstrated with Tm3+, Nd3+ or Pr3+-doped nanocrystals, but their emission is limited to 600 and 800 nm, restricting applications. Here, we utilize Gd3+-assisted energy migration to tune the emission wavelengths of Tm3+-sensitized ANPs and generate highly nonlinear emission of Eu3+, Tb3+, Ho3+, and Er3+ ions. The upconversion intensities of these spectrally discrete ANPs scale with the nonlinearity factor s = 10-17 under 1064 nm excitation at power densities as low as 6 kW/cm2. This strategy for imprinting avalanche behavior on remote emitters can be extended to fluorophores adjacent to ANPs, as we demonstrate with CdS/CdSe/CdS core/shell/shell quantum dots. ANPs with rationally designed energy transfer networks provide the means to transform conventional linear emitters into a highly nonlinear ones, expanding the use of photon avalanching in biological, chemical, and photonic applications., Comment: 13 pages, 5 figures

Serverless computing has become increasingly popular for machine learning inference. However, current serverless platforms lack efficient support for GPUs, limiting their ability to deliver low-latency inference. In this paper, we propose FaaSwap, a GPU-efficient serverless inference platform. FaaSwap employs a holistic approach to system and algorithm design. It maintains models in main memory and dynamically swaps them onto GPUs upon request arrivals (i.e., late binding), thereby enabling a large number of inference functions to efficiently share a node's GPUs. FaaSwap uses various techniques, including asynchronous API redirection, GPU runtime sharing, pipelined model execution, and efficient GPU memory management, to achieve the optimal performance. We also develop an interference-aware request scheduling algorithm that allows FaaSwap to meet the latency SLOs for individual inference functions. We have implemented FaaSwap as a prototype on a leading commercial serverless platform. Experimental evaluations demonstrate that, with model swapping, FaaSwap can concurrently serve hundreds of functions on a single worker node with 4 V100 GPUs, while achieving inference performance comparable to native execution (where each function runs on a dedicated GPU). When deployed on a 6-node production testbed, FaaSwap meets the latency SLOs for over 1k functions, the maximum that the testbed can handle concurrently.

We investigate thermodynamics of general nonequilibrium processes stopped at stochastic times. We propose a systematic strategy for constructing fluctuation-theorem-like martingales for each thermodynamic functional, yielding a family of stopping-time fluctuation theorems. We derive second-law-like thermodynamic inequalities for the mean thermodynamic functional at stochastic stopping times, the bounds of which are stronger than the thermodynamic inequalities resulting from the traditional fluctuation theorems when the stopping time is reduced to a deterministic one. Numerical verification is carried out for three well-known thermodynamic functionals, namely, entropy production, free energy dissipation and dissipative work. These universal equalities and inequalities are valid for arbitrary stopping strategies, and thus provide a comprehensive framework with new insights into the fundamental principles governing nonequilibrium systems., Comment: 7 pages, 2 figures

We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: we build an anti-LM based on previously generated text and use this anti-LM to penalize future generation of what has been generated. The anti-LM can be implemented as simple as an n-gram language model or a vectorized variant. In this way, FSD introduces no extra model parameters and negligible computational overhead (FSD can be as fast as greedy search). Despite the simplicity, FSD is surprisingly effective; Experiments show that FSD can outperform the canonical methods to date (i.e., nucleus sampling) as well as several strong baselines that were proposed recently., Comment: LREC-Coling 2024

Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even when trained without parallel data. Yet, despite the fact that the amount of training data is gigantic, they still struggle with translating rare words, particularly for low-resource languages. Even worse, it is usually unrealistic to retrieve relevant demonstrations for in-context learning with low-resource languages on LLMs, which restricts the practical use of LLMs for translation -- how should we mitigate this problem? To this end, we present a novel method, CoD, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities for LLMs. Extensive experiments indicate that augmenting ChatGPT with CoD elicits large gains by up to 13x chrF++ points for MNMT (3.08 to 42.63 for English to Serbian written in Cyrillic script) on FLORES-200 full devtest set. We further demonstrate the importance of chaining the multilingual dictionaries, as well as the superiority of CoD to few-shot demonstration for low-resource languages.

Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always yields an entirely new model for each task. Currently, many research works propose to only fine-tune a small portion of the parameters while keeping most of the parameters shared across different tasks. These methods achieve surprisingly good performance and are shown to be more stable than their corresponding fully fine-tuned counterparts. However, such kind of methods is still not well understood. Some natural questions arise: How does the parameter sparsity lead to promising performance? Why is the model more stable than the fully fine-tuned models? How to choose the tunable parameters? In this paper, we first categorize the existing methods into random approaches, rule-based approaches, and projection-based approaches based on how they choose which parameters to tune. Then, we show that all of the methods are actually sparse fine-tuned models and conduct a novel theoretical analysis of them. We indicate that the sparsity is actually imposing a regularization on the original model by controlling the upper bound of the stability. Such stability leads to better generalization capability which has been empirically observed in a lot of recent research works. Despite the effectiveness of sparsity grounded by our theory, it still remains an open problem of how to choose the tunable parameters. To better choose the tunable parameters, we propose a novel Second-order Approximation Method (SAM) which approximates the original problem with an analytically solvable optimization function. The tunable parameters are determined by directly optimizing the approximation function. The experimental results show that our proposed SAM model outperforms many strong baseline models and it also verifies our theoretical analysis.

The rapid advances in automation technologies, such as artificial intelligence (AI) and robotics, pose an increasing risk of automation for occupations, with a likely significant impact on the labour market. Recent social-economic studies suggest that nearly 50\% of occupations are at high risk of being automated in the next decade. However, the lack of granular data and empirically informed models have limited the accuracy of these studies and made it challenging to predict which jobs will be automated. In this paper, we study the automation risk of occupations by performing a classification task between automated and non-automated occupations. The available information is 910 occupations' task statements, skills and interactions categorised by Standard Occupational Classification (SOC). To fully utilize this information, we propose a graph-based semi-supervised classification method named \textbf{A}utomated \textbf{O}ccupation \textbf{C}lassification based on \textbf{G}raph \textbf{C}onvolutional \textbf{N}etworks (\textbf{AOC-GCN}) to identify the automated risk for occupations. This model integrates a heterogeneous graph to capture occupations' local and global contexts. The results show that our proposed method outperforms the baseline models by considering the information of both internal features of occupations and their external interactions. This study could help policymakers identify potential automated occupations and support individuals' decision-making before entering the job market., Comment: 15 pages, 6 figures

Currently, graph learning models are indispensable tools to help researchers explore graph-structured data. In academia, using sufficient training data to optimize a graph model on a single device is a typical approach for training a capable graph learning model. Due to privacy concerns, however, it is infeasible to do so in real-world scenarios. Federated learning provides a practical means of addressing this limitation by introducing various privacy-preserving mechanisms, such as differential privacy (DP) on the graph edges. However, although DP in federated graph learning can ensure the security of sensitive information represented in graphs, it usually causes the performance of graph learning models to degrade. In this paper, we investigate how DP can be implemented on graph edges and observe a performance decrease in our experiments. In addition, we note that DP on graph edges introduces noise that perturbs graph proximity, which is one of the graph augmentations in graph contrastive learning. Inspired by this, we propose leveraging graph contrastive learning to alleviate the performance drop resulting from DP. Extensive experiments conducted with four representative graph models on five widely used benchmark datasets show that contrastive learning indeed alleviates the models' DP-induced performance drops., Comment: Accepted by Information Sciences

Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as contrasting pairs for the purpose of learning underlying structural semantics of the input graph. Recent works usually sample negative samples from the same training batch with the positive samples, or from an external irrelevant graph. However, a significant limitation lies in such strategies, which is the unavoidable problem of sampling false negative samples. In this paper, we propose a novel method to utilize \textbf{C}ounterfactual mechanism to generate artificial hard negative samples for \textbf{G}raph \textbf{C}ontrastive learning, namely \textbf{CGC}, which has a different perspective compared to those sampling-based strategies. We utilize counterfactual mechanism to produce hard negative samples, which ensures that the generated samples are similar to, but have labels that different from the positive sample. The proposed method achieves satisfying results on several datasets compared to some traditional unsupervised graph learning methods and some SOTA graph contrastive learning methods. We also conduct some supplementary experiments to give an extensive illustration of the proposed method, including the performances of CGC with different hard negative samples and evaluations for hard negative samples generated with different similarity measurements., Comment: ACCEPTED BY WWW'2023

Maintaining a consistent persona is essential for building a human-like conversational model. However, the lack of attention to the partner makes the model more egocentric: they tend to show their persona by all means such as twisting the topic stiffly, pulling the conversation to their own interests regardless, and rambling their persona with little curiosity to the partner. In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity toward the partner, leading responses around mutual personas, and finding the common ground. Specifically, we first represent self-persona, partner persona and mutual dialogue all in the concept sets. Then, we propose the Concept Set framework with a suite of knowledge-enhanced operations to process them such as set algebras, set expansion, and set distance. Based on these operations as medium, we train the model by utilizing 1) concepts of both party personas, 2) concept relationship between them, and 3) their relationship to the future dialogue. Extensive experiments on a large public dataset, Persona-Chat, demonstrate that our model outperforms state-of-the-art baselines for generating less egocentric, more human-like, and higher quality responses in both automatic and human evaluations., Comment: Accepted by SIGIR 2022, 11 pages, 9 figures

Parameter-efficient tuning aims to distill knowledge for downstream tasks by optimizing a few introduced parameters while freezing the pretrained language models (PLMs). Continuous prompt tuning which prepends a few trainable vectors to the embeddings of input is one of these methods and has drawn much attention due to its effectiveness and efficiency. This family of methods can be illustrated as exerting nonlinear transformations of hidden states inside PLMs. However, a natural question is ignored: can the hidden states be directly used for classification without changing them? In this paper, we aim to answer this question by proposing a simple tuning method which only introduces three trainable vectors. Firstly, we integrate all layers hidden states using the introduced vectors. And then, we input the integrated hidden state(s) to a task-specific linear classifier to predict categories. This scheme is similar to the way ELMo utilises hidden states except that they feed the hidden states to LSTM-based models. Although our proposed tuning scheme is simple, it achieves comparable performance with prompt tuning methods like P-tuning and P-tuning v2, verifying that original hidden states do contain useful information for classification tasks. Moreover, our method has an advantage over prompt tuning in terms of time and the number of parameters.