PyTorchKR Papers

최신 논문

총 11,878편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2402.07087공식 코드 · Papers with Code

Self-Correcting Self-Consuming Loops for Generative Model Training

As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite the successful stories of using synthetic data for representation learning, using synthetic data for generative model training creates "self-consuming loops" which may lead to training instability or even collapse, unless certain conditions are met. Our paper aims to stabilize self-consuming generative model training. Our theoretical results demonstrate that by introducing an idealized correction function, which maps a data point to be more likely under the true data distribution, self-consuming loops can be made exponentially more stable. We then propose self-correction functions, which rely on expert knowledge (e.g. the laws of physics programmed in a simulator), and aim to approximate the idealized corrector automatically and at scale. We empirically validate the effectiveness of self-correcting self-consuming loops on the challenging human motion synthesis task, and observe that it successfully avoids model collapse, even when the ratio of synthetic data to real data is as high as 100%.

arXiv:2402.05962

EXGC: Bridging Efficiency and Explainability in Graph Condensation

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC.

arXiv:2402.05952

Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniques

The integration of Large Language Models (LLMs) with Graph Representation Learning (GRL) marks a significant evolution in analyzing complex data structures. This collaboration harnesses the sophisticated linguistic capabilities of LLMs to improve the contextual understanding and adaptability of graph models, thereby broadening the scope and potential of GRL. Despite a growing body of research dedicated to integrating LLMs into the graph domain, a comprehensive review that deeply analyzes the core components and operations within these models is notably lacking. Our survey fills this gap by proposing a novel taxonomy that breaks down these models into primary components and operation techniques from a novel technical perspective. We further dissect recent literature into two primary components including knowledge extractors and organizers, and two operation techniques including integration and training stratigies, shedding light on effective model design and training strategies. Additionally, we identify and explore potential future research avenues in this nascent yet underexplored field, proposing paths for continued progress.

arXiv:2402.06525

Flexible infinite-width graph convolutional networks and the importance of representation learning

A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed. This is known as a neural network Gaussian process (NNGP). However, the NNGP kernel is fixed, and tunable only through a small number of hyperparameters, eliminating any possibility of representation learning. This contrasts with finite-width NNs, which are often believed to perform well precisely because they are able to learn representations. Thus in simplifying NNs to make them theoretically tractable, NNGPs may eliminate precisely what makes them work well (representation learning). This motivated us to understand whether representation learning is necessary in a range of graph classification tasks. We develop a precise tool for this task, the graph convolutional deep kernel machine. This is very similar to an NNGP, in that it is an infinite width limit and uses kernels, but comes with a `knob' to control the amount of representation learning. We found that representation learning is necessary (in the sense that it gives dramatic performance improvements) in graph classification tasks and heterophilous node classification tasks, but not in homophilous node classification tasks.

arXiv:2402.06367공식 코드 · Papers with Code

TEE4EHR: Transformer Event Encoder for Better Representation Learning in Electronic Health Records

Irregular sampling of time series in electronic health records (EHRs) is one of the main challenges for developing machine learning models. Additionally, the pattern of missing data in certain clinical variables is not at random but depends on the decisions of clinicians and the state of the patient. Point process is a mathematical framework for analyzing event sequence data that is consistent with irregular sampling patterns. Our model, TEE4EHR, is a transformer event encoder (TEE) with point process loss that encodes the pattern of laboratory tests in EHRs. The utility of our TEE has been investigated in a variety of benchmark event sequence datasets. Additionally, we conduct experiments on two real-world EHR databases to provide a more comprehensive evaluation of our model. Firstly, in a self-supervised learning approach, the TEE is jointly learned with an existing attention-based deep neural network which gives superior performance in negative log-likelihood and future event prediction. Besides, we propose an algorithm for aggregating attention weights that can reveal the interaction between the events. Secondly, we transfer and freeze the learned TEE to the downstream task for the outcome prediction, where it outperforms state-of-the-art models for handling irregularly sampled time series. Furthermore, our results demonstrate that our approach can improve representation learning in EHRs and can be useful for clinical prediction tasks.

arXiv:2402.06135

Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning

The electronic map plays a crucial role in geographic information systems, serving various urban managerial scenarios and daily life services. Developing effective Map Entity Representation Learning (MERL) methods is crucial to extracting embedding information from electronic maps and converting map entities into representation vectors for downstream applications. However, existing MERL methods typically focus on one specific category of map entities, such as POIs, road segments, or land parcels, which is insufficient for real-world diverse map-based applications and might lose latent structural and semantic information interacting between entities of different types. Moreover, using representations generated by separate models for different map entities can introduce inconsistencies. Motivated by this, we propose a novel method named HOME-GCL for learning representations of multiple categories of map entities. Our approach utilizes a heterogeneous map entity graph (HOME graph) that integrates both road segments and land parcels into a unified framework. A HOME encoder with parcel-segment joint feature encoding and heterogeneous graph transformer is then deliberately designed to convert segments and parcels into representation vectors. Moreover, we introduce two types of contrastive learning tasks, namely intra-entity and inter-entity tasks, to train the encoder in a self-supervised manner. Extensive experiments on three large-scale datasets covering road segment-based, land parcel-based, and trajectory-based tasks demonstrate the superiority of our approach. To the best of our knowledge, HOME-GCL is the first attempt to jointly learn representations for road segments and land parcels using a unified model.

arXiv:2402.06010공식 코드 · Papers with Code

NPSVC++: Nonparallel Classifiers Encounter Representation Learning

This paper focuses on a specific family of classifiers called nonparallel support vector classifiers (NPSVCs). Different from typical classifiers, the training of an NPSVC involves the minimization of multiple objectives, resulting in the potential concerns of feature suboptimality and class dependency. Consequently, no effective learning scheme has been established to improve NPSVCs' performance through representation learning, especially deep learning. To break this bottleneck, we develop NPSVC++ based on multi-objective optimization, enabling the end-to-end learning of NPSVC and its features. By pursuing Pareto optimality, NPSVC++ theoretically ensures feature optimality across classes, hence effectively overcoming the two issues above. A general learning procedure via duality optimization is proposed, based on which we provide two applicable instances, K-NPSVC++ and D-NPSVC++. The experiments show their superiority over the existing methods and verify the efficacy of NPSVC++.

arXiv:2402.06223

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

Directed acyclic graphs (DAGs) are fundamental graph structures in causal modeling, but identifying the desired DAG from observational data often requires strong assumptions that may not hold in real-world scenarios, especially for latent causal models and complex multimodal data. This raises the question of whether we can relax or bypass the DAG assumption while maintaining practical utility. In this work, we propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities. Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation. This result deepens our understanding of the why multimodal contrastive learning works, highlights its potential for disentanglement, and expands the utility of pre-trained models like CLIP. Synthetic experiments confirm the robustness of our findings, even when the assumptions are partially violated. Most importantly, experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets. Together, these contributions push the boundaries of multimodal contrastive learning, both theoretically and, crucially, in practical applications.

arXiv:2402.06326

Prompt Learning on Temporal Interaction Graphs

Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps between the pre-training and downstream predictions in their ``pre-train, predict'' training paradigm. First, the temporal discrepancy between the pre-training and inference data severely undermines the models' applicability in distant future predictions on the dynamically evolving data. Second, the semantic divergence between pretext and downstream tasks hinders their practical applications, as they struggle to align with their learning and prediction capabilities across application scenarios. Recently, the ``pre-train, prompt'' paradigm has emerged as a lightweight mechanism for model generalization. Applying this paradigm is a potential solution to solve the aforementioned challenges. However, the adaptation of this paradigm to TIGs is not straightforward. The application of prompting in static graph contexts falls short in temporal settings due to a lack of consideration for time-sensitive dynamics and a deficiency in expressive power. To address this issue, we introduce Temporal Interaction Graph Prompting (TIGPrompt), a versatile framework that seamlessly integrates with TIG models, bridging both the temporal and semantic gaps. In detail, we propose a temporal prompt generator to offer temporally-aware prompts for different tasks. These prompts stand out for their minimalistic design, relying solely on the tuning of the prompt generator with very little supervision data. To cater to varying computational resource demands, we propose an extended ``pre-train, prompt-based fine-tune'' paradigm, offering greater flexibility. Through extensive experiments, the TIGPrompt demonstrates the SOTA performance and remarkable efficiency advantages.

arXiv:2402.06188

A self-supervised framework for learning whole slide representations

Whole slide imaging is fundamental to biomedical microscopy and computational pathology. Previously, learning representations for gigapixel-sized whole slide images (WSIs) has relied on multiple instance learning with weak labels, which do not annotate the diverse morphologic features and spatial heterogeneity of WSIs. A high-quality self-supervised learning method for WSIs would provide transferable visual representations for downstream computational pathology tasks, without the need for dense annotations. We present Slide Pre-trained Transformers (SPT) for gigapixel-scale self-supervision of WSIs. Treating WSI patches as tokens, SPT combines data transformation strategies from language and vision modeling into a general and unified framework to generate views of WSIs for self-supervised pretraining. SPT leverages the inherent regional heterogeneity, histologic feature variability, and information redundancy within WSIs to learn high-quality whole slide representations. We benchmark SPT visual representations on five diagnostic tasks across three biomedical microscopy datasets. SPT significantly outperforms baselines for histopathologic diagnosis, cancer subtyping, and genetic mutation prediction. Finally, we demonstrate that SPT consistently improves whole slide representations when using off-the-shelf, in-domain, and foundational patch encoders for whole slide multiple instance learning.

arXiv:2402.06187공식 코드 · Papers with Code

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a general feature representation, which captures critical environmental dynamics and is fine-tuned using minimal expert demonstrations. It advances the temporal action contrastive learning (TACO) objective, known for state-of-the-art results in visual control tasks, by incorporating a novel negative example sampling strategy. This strategy is crucial in significantly boosting TACO's computational efficiency, making large-scale multitask offline pretraining feasible. Our extensive empirical evaluation in a diverse set of continuous control benchmarks including Deepmind Control Suite, MetaWorld, and LIBERO demonstrate Premier-TACO's effectiveness in pretraining visual representations, significantly enhancing few-shot imitation learning of novel tasks. Our code, pretraining data, as well as pretrained model checkpoints will be released at https://github.com/PremierTACO/premier-taco. Our project webpage is at https://premiertaco.github.io.

arXiv:2402.06038

Contrastive Approach to Prior Free Positive Unlabeled Learning

Positive Unlabeled (PU) learning refers to the task of learning a binary classifier given a few labeled positive samples, and a set of unlabeled samples (which could be positive or negative). In this paper, we propose a novel PU learning framework, that starts by learning a feature space through pretext-invariant representation learning and then applies pseudo-labeling to the unlabeled examples, leveraging the concentration property of the embeddings. Overall, our proposed approach handily outperforms state-of-the-art PU learning methods across several standard PU benchmark datasets, while not requiring a-priori knowledge or estimate of class prior. Remarkably, our method remains effective even when labeled data is scant, where most PU learning algorithms falter. We also provide simple theoretical analysis motivating our proposed algorithms and establish generalization guarantee for our approach.

arXiv:2402.05916

GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory

We present GenEFT: an effective theory framework for shedding light on the statics and dynamics of neural network generalization, and illustrate it with graph learning examples. We first investigate the generalization phase transition as data size increases, comparing experimental results with information-theory-based approximations. We find generalization in a Goldilocks zone where the decoder is neither too weak nor too powerful. We then introduce an effective theory for the dynamics of representation learning, where latent-space representations are modeled as interacting particles (repons), and find that it explains our experimentally observed phase transition between generalization and overfitting as encoder and decoder learning rates are scanned. This highlights the power of physics-inspired effective theories for bridging the gap between theoretical predictions and practice in machine learning.

arXiv:2402.05396공식 코드 · Papers with Code

TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning

Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommendation. Despite the success of TGNNs, they are prone to the prevalent noise found in real-world dynamic graphs like time-deprecated links and skewed interaction distribution. The noise causes two critical issues that significantly compromise the accuracy of TGNNs: (1) models are supervised by inferior interactions, and (2) noisy input induces high variance in the aggregated messages. However, current TGNN denoising techniques do not consider the diverse and dynamic noise pattern of each node. In addition, they also suffer from the excessive mini-batch generation overheads caused by traversing more neighbors. We believe the remedy for fast and accurate TGNNs lies in temporal adaptive sampling. In this work, we propose TASER, the first adaptive sampling method for TGNNs optimized for accuracy, efficiency, and scalability. TASER adapts its mini-batch selection based on training dynamics and temporal neighbor selection based on the contextual, structural, and temporal properties of past interactions. To alleviate the bottleneck in mini-batch generation, TASER implements a pure GPU-based temporal neighbor finder and a dedicated GPU feature cache. We evaluate the performance of TASER using two state-of-the-art backbone TGNNs. On five popular datasets, TASER outperforms the corresponding baselines by an average of 2.3% in Mean Reciprocal Rank (MRR) while achieving an average of 5.1x speedup in training time.

arXiv:2402.05052

Causal Representation Learning from Multiple Distributions: A General Setting

In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing environments or making proper changes to the system, it is helpful to recover the latent causal variables $Z_i$ and their causal relations represented by graph $\mathcal{G}_Z$. This problem has recently been known as causal representation learning. This paper is concerned with a general, completely nonparametric setting of causal representation learning from multiple distributions (arising from heterogeneous data or nonstationary time series), without assuming hard interventions behind distribution changes. We aim to develop general solutions in this fundamental case; as a by product, this helps see the unique benefit offered by other assumptions such as parametric causal models or hard interventions. We show that under the sparsity constraint on the recovered graph over the latent variables and suitable sufficient change conditions on the causal influences, interestingly, one can recover the moralized graph of the underlying directed acyclic graph, and the recovered latent variables and their relations are related to the underlying causal model in a specific, nontrivial way. In some cases, most latent variables can even be recovered up to component-wise transformations. Experimental results verify our theoretical claims.

arXiv:2402.04924공식 코드 · Papers with Code

Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching

Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns. As one of the most promising directions, graph condensation methods address these issues by employing gradient matching, aiming to condense the full graph into a more concise yet information-rich synthetic set. Though encouraging, these strategies primarily emphasize matching directions of the gradients, which leads to deviations in the training trajectories. Such deviations are further magnified by the differences between the condensation and evaluation phases, culminating in accumulated errors, which detrimentally affect the performance of the condensed graphs. In light of this, we propose a novel graph condensation method named \textbf{C}raf\textbf{T}ing \textbf{R}ationa\textbf{L} trajectory (\textbf{CTRL}), which offers an optimized starting point closer to the original dataset's feature distribution and a more refined strategy for gradient matching. Theoretically, CTRL can effectively neutralize the impact of accumulated errors on the performance of condensed graphs. We provide extensive experiments on various graph datasets and downstream tasks to support the effectiveness of CTRL. Code is released at https://github.com/NUS-HPC-AI-Lab/CTRL.

arXiv:2402.04852공식 코드 · Papers with Code

Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning

In this study, we present aLLM4TS, an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning. Central to our approach is that we reconceive time-series forecasting as a self-supervised, multi-patch prediction task, which, compared to traditional contrastive learning or mask-and-reconstruction methods, captures temporal dynamics in patch representations more effectively. Our strategy encompasses two-stage training: (i). a causal continual pre-training phase on various time-series datasets, anchored on next patch prediction, effectively syncing LLM capabilities with the intricacies of time-series data; (ii). fine-tuning for multi-patch prediction in the targeted time-series context. A distinctive element of our framework is the patch-wise decoding layer, which departs from previous methods reliant on sequence-level decoding. Such a design directly transposes individual patches into temporal sequences, thereby significantly bolstering the model's proficiency in mastering temporal patch-based representations. aLLM4TS demonstrates superior performance in several downstream tasks, proving its effectiveness in deriving temporal representations with enhanced transferability and marking a pivotal advancement in the adaptation of LLMs for time-series analysis.

arXiv:2402.04567공식 코드 · Papers with Code

OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences

Anomaly detection in decision-making sequences is a challenging problem due to the complexity of normality representation learning and the sequential nature of the task. Most existing methods based on Reinforcement Learning (RL) are difficult to implement in the real world due to unrealistic assumptions, such as having access to environment dynamics, reward signals, and online interactions with the environment. To address these limitations, we propose an unsupervised method named Offline Imitation Learning based Anomaly Detection (OIL-AD), which detects anomalies in decision-making sequences using two extracted behaviour features: action optimality and sequential association. Our offline learning model is an adaptation of behavioural cloning with a transformer policy network, where we modify the training process to learn a Q function and a state value function from normal trajectories. We propose that the Q function and the state value function can provide sufficient information about agents' behavioural data, from which we derive two features for anomaly detection. The intuition behind our method is that the action optimality feature derived from the Q function can differentiate the optimal action from others at each local state, and the sequential association feature derived from the state value function has the potential to maintain the temporal correlations between decisions (state-action pairs). Our experiments show that OIL-AD can achieve outstanding online anomaly detection performance with up to 34.8% improvement in F1 score over comparable baselines.

arXiv:2402.03386

A generalized decision tree ensemble based on the NeuralNetworks architecture: Distributed Gradient Boosting Forest (DGBF)

Tree ensemble algorithms as RandomForest and GradientBoosting are currently the dominant methods for modeling discrete or tabular data, however, they are unable to perform a hierarchical representation learning from raw data as NeuralNetworks does thanks to its multi-layered structure, which is a key feature for DeepLearning problems and modeling unstructured data. This limitation is due to the fact that tree algorithms can not be trained with back-propagation because of their mathematical nature. However, in this work, we demonstrate that the mathematical formulation of bagging and boosting can be combined together to define a graph-structured-tree-ensemble algorithm with a distributed representation learning process between trees naturally (without using back-propagation). We call this novel approach Distributed Gradient Boosting Forest (DGBF) and we demonstrate that both RandomForest and GradientBoosting can be expressed as particular graph architectures of DGBT. Finally, we see that the distributed learning outperforms both RandomForest and GradientBoosting in 7 out of 9 datasets.

arXiv:2402.04033

On provable privacy vulnerabilities of graph representations

Graph representation learning (GRL) is critical for extracting insights from complex network structures, but it also raises security concerns due to potential privacy vulnerabilities in these representations. This paper investigates the structural vulnerabilities in graph neural models where sensitive topological information can be inferred through edge reconstruction attacks. Our research primarily addresses the theoretical underpinnings of similarity-based edge reconstruction attacks (SERA), furnishing a non-asymptotic analysis of their reconstruction capacities. Moreover, we present empirical corroboration indicating that such attacks can perfectly reconstruct sparse graphs as graph size increases. Conversely, we establish that sparsity is a critical factor for SERA's effectiveness, as demonstrated through analysis and experiments on (dense) stochastic block models. Finally, we explore the resilience of private graph representations produced via noisy aggregation (NAG) mechanism against SERA. Through theoretical analysis and empirical assessments, we affirm the mitigation of SERA using NAG . In parallel, we also empirically delineate instances wherein SERA demonstrates both efficacy and deficiency in its capacity to function as an instrument for elucidating the trade-off between privacy and utility.