PyTorchKR Papers

최신 논문

총 139,336편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2502.19922공식 코드 · Papers with Code

Incremental Learning with Repetition via Pseudo-Feature Projection

Incremental Learning scenarios do not always represent real-world inference use-cases, which tend to have less strict task boundaries, and exhibit repetition of common classes and concepts in their continual data stream. To better represent these use-cases, new scenarios with partial repetition and mixing of tasks are proposed, where the repetition patterns are innate to the scenario and unknown to the strategy. We investigate how exemplar-free incremental learning strategies are affected by data repetition, and we adapt a series of state-of-the-art approaches to analyse and fairly compare them under both settings. Further, we also propose a novel method (Horde), able to dynamically adjust an ensemble of self-reliant feature extractors, and align them by exploiting class repetition. Our proposed exemplar-free method achieves competitive results in the classic scenario without repetition, and state-of-the-art performance in the one with repetition.

arXiv:2502.19921공식 코드 · Papers with Code

Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning

Deep learning models lack shift invariance, making them sensitive to input shifts that cause changes in output. While recent techniques seek to address this for images, our findings show that these approaches fail to provide shift-invariance in time series, where the data generation mechanism is more challenging due to the interaction of low and high frequencies. Worse, they also decrease performance across several tasks. In this paper, we propose a novel differentiable bijective function that maps samples from their high-dimensional data manifold to another manifold of the same dimension, without any dimensional reduction. Our approach guarantees that samples -- when subjected to random shifts -- are mapped to a unique point in the manifold while preserving all task-relevant information without loss. We theoretically and empirically demonstrate that the proposed transformation guarantees shift-invariance in deep learning models without imposing any limits to the shift. Our experiments on six time series tasks with state-of-the-art methods show that our approach consistently improves the performance while enabling models to achieve complete shift-invariance without modifying or imposing restrictions on the model's topology. The source code is available on \href{https://github.com/eth-siplab/Shifting-the-Paradigm}{GitHub}.

arXiv:2502.19920공식 코드 · Papers with Code

Playing Pokémon Red via Deep Reinforcement Learning

Pok\'emon Red, a classic Game Boy JRPG, presents significant challenges as a testbed for agents, including multi-tasking, long horizons of tens of thousands of steps, hard exploration, and a vast array of potential policies. We introduce a simplistic environment and a Deep Reinforcement Learning (DRL) training methodology, demonstrating a baseline agent that completes an initial segment of the game up to completing Cerulean City. Our experiments include various ablations that reveal vulnerabilities in reward shaping, where agents exploit specific reward signals. We also discuss limitations and argue that games like Pok\'emon hold strong potential for future research on Large Language Model agents, hierarchical training algorithms, and advanced exploration methods. Source Code: https://github.com/MarcoMeter/neroRL/tree/poke_red

arXiv:2502.19805공식 코드 · Papers with Code

Implicit Search via Discrete Diffusion: A Study on Chess

In the post-AlphaGo era, there has been a renewed interest in search techniques such as Monte Carlo Tree Search (MCTS), particularly in their application to Large Language Models (LLMs). This renewed attention is driven by the recognition that current next-token prediction models often lack the ability for long-term planning. Is it possible to instill search-like abilities within the models to enhance their planning abilities without relying on explicit search? We propose DiffuSearch , a model that does \textit{implicit search} by looking into the future world via discrete diffusion modeling. We instantiate DiffuSearch on a classical board game, Chess, where explicit search is known to be essential. Through extensive controlled experiments, we show DiffuSearch outperforms both the searchless and explicit search-enhanced policies. Specifically, DiffuSearch outperforms the one-step policy by 19.2% and the MCTS-enhanced policy by 14% on action accuracy. Furthermore, DiffuSearch demonstrates a notable 30% enhancement in puzzle-solving abilities compared to explicit search-based policies, along with a significant 540 Elo increase in game-playing strength assessment. These results indicate that implicit search via discrete diffusion is a viable alternative to explicit search over a one-step policy. All codes are publicly available at \href{https://github.com/HKUNLP/DiffuSearch}{https://github.com/HKUNLP/DiffuSearch}.

arXiv:2502.19787공식 코드 · Papers with Code

In-Context Learning with Hypothesis-Class Guidance

Recent research has investigated the underlying mechanisms of in-context learning (ICL) both theoretically and empirically, often using data generated from simple function classes. However, the existing work often focuses on the sequence consisting solely of labeled examples, while in practice, labeled examples are typically accompanied by an instruction, providing some side information about the task. In this work, we propose ICL with hypothesis-class guidance (ICL-HCG), a novel synthetic data model for ICL where the input context consists of the literal description of a (finite) hypothesis class $\mathcal{H}$ and $(x,y)$ pairs from a hypothesis chosen from $\mathcal{H}$. Under our framework ICL-HCG, we conduct extensive experiments to explore: (i) a variety of generalization abilities to new hypothesis classes; (ii) different model architectures; (iii) sample complexity; (iv) in-context data imbalance; (v) the role of instruction; and (vi) the effect of pretraining hypothesis diversity. As a result, we show that (a) Transformers can successfully learn ICL-HCG and generalize to unseen hypotheses and unseen hypothesis classes, and (b) compared with ICL without instruction, ICL-HCG achieves significantly higher accuracy, demonstrating the role of instructions.

arXiv:2502.19750공식 코드 · Papers with Code

CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer

Accurate Subseasonal-to-Seasonal (S2S) climate forecasting is pivotal for decision-making including agriculture planning and disaster preparedness but is known to be challenging due to its chaotic nature. Although recent data-driven models have shown promising results, their performance is limited by inadequate consideration of geometric inductive biases. Usually, they treat the spherical weather data as planar images, resulting in an inaccurate representation of locations and spatial relations. In this work, we propose the geometric-inspired Circular Transformer (CirT) to model the cyclic characteristic of the graticule, consisting of two key designs: (1) Decomposing the weather data by latitude into circular patches that serve as input tokens to the Transformer; (2) Leveraging Fourier transform in self-attention to capture the global information and model the spatial periodicity. Extensive experiments on the Earth Reanalysis 5 (ERA5) reanalysis dataset demonstrate our model yields a significant improvement over the advanced data-driven models, including PanguWeather and GraphCast, as well as skillful ECMWF systems. Additionally, we empirically show the effectiveness of our model designs and high-quality prediction over spatial and temporal dimensions.

arXiv:2502.19742공식 코드 · Papers with Code

BiRating -- Iterative averaging on a bipartite graph of Beat Saber scores, player skills, and map difficulties

Difficulty estimation of Beat Saber maps is an interesting data analysis problem and valuable to the Beat Saber competitive scene. We present a simple algorithm that iteratively averages player skill and map difficulty estimations in a bipartite graph of players and maps, connected by scores, using scores only as input. This approach simultaneously estimates player skills and map difficulties, exploiting each of them to improve the estimation of the other, exploitng the relation of multiple scores by different players on the same map, or on different maps by the same player. While we have been unable to prove or characterize theoretical convergence, the implementation exhibits convergent behaviour to low estimation error in all instances, producing accurate results. An informal qualitative evaluation involving experienced Beat Saber community members was carried out, comparing the difficulty estimations output by our algorithm with their personal perspectives on the difficulties of different maps. There was a significant alignment with player perceived perceptions of difficulty and with other existing methods for estimating difficulty. Our approach showed significant improvement over existing methods in certain known problematic maps that are not typically accurately estimated, but also produces problematic estimations for certain families of maps where the assumptions on the meaning of scores were inadequate (e.g. not enough scores, or scores over optimized by players). The algorithm has important limitations, related to data quality and meaningfulness, assumptions on the domain problem, and theoretical convergence of the algorithm. Future work would significantly benefit from a better understanding of adequate ways to quantify map difficulty in Beat Saber, including multidimensionality of skill and difficulty, and the systematic biases present in score data.

arXiv:2502.19693공식 코드 · Papers with Code

Accurate and Scalable Graph Neural Networks via Message Invariance

Message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. For a sampled mini-batch of target nodes, the message passing process is divided into two parts: message passing between nodes within the batch (MP-IB) and message passing from nodes outside the batch to those within it (MP-OB). However, MP-OB recursively relies on higher-order out-of-batch neighbors, leading to an exponentially growing computational cost with respect to the number of layers. Due to the neighbor explosion, the whole message passing stores most nodes and edges on the GPU such that many GNNs are infeasible to large-scale graphs. To address this challenge, we propose an accurate and fast mini-batch approach for large graph transductive learning, namely topological compensation (TOP), which obtains the outputs of the whole message passing solely through MP-IB, without the costly MP-OB. The major pillar of TOP is a novel concept of message invariance, which defines message-invariant transformations to convert costly MP-OB into fast MP-IB. This ensures that the modified MP-IB has the same output as the whole message passing. Experiments demonstrate that TOP is significantly faster than existing mini-batch methods by order of magnitude on vast graphs (millions of nodes and billions of edges) with limited accuracy degradation.

arXiv:2502.19670공식 코드 · Papers with Code

Training Robust Graph Neural Networks by Modeling Noise Dependencies

In real-world applications, node features in graphs often contain noise from various sources, leading to significant performance degradation in GNNs. Although several methods have been developed to enhance robustness, they rely on the unrealistic assumption that noise in node features is independent of the graph structure and node labels, thereby limiting their applicability. To this end, we introduce a more realistic noise scenario, dependency-aware noise on graphs (DANG), where noise in node features create a chain of noise dependencies that propagates to the graph structure and node labels. We propose a novel robust GNN, DA-GNN, which captures the causal relationships among variables in the data generating process (DGP) of DANG using variational inference. In addition, we present new benchmark datasets that simulate DANG in real-world applications, enabling more practical research on robust GNNs. Extensive experiments demonstrate that DA-GNN consistently outperforms existing baselines across various noise scenarios, including both DANG and conventional noise models commonly considered in this field.

arXiv:2502.19665공식 코드 · Papers with Code

Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization

Invariant risk minimization is an important general machine learning framework that has recently been interpreted as a total variation model (IRM-TV). However, how to improve out-of-distribution (OOD) generalization in the IRM-TV setting remains unsolved. In this paper, we extend IRM-TV to a Lagrangian multiplier model named OOD-TV-IRM. We find that the autonomous TV penalty hyperparameter is exactly the Lagrangian multiplier. Thus OOD-TV-IRM is essentially a primal-dual optimization model, where the primal optimization minimizes the entire invariant risk and the dual optimization strengthens the TV penalty. The objective is to reach a semi-Nash equilibrium where the balance between the training loss and OOD generalization is maintained. We also develop a convergent primal-dual algorithm that facilitates an adversarial learning scheme. Experimental results show that OOD-TV-IRM outperforms IRM-TV in most situations.

arXiv:2502.19611공식 코드 · Papers with Code

PRDP: Progressively Refined Differentiable Physics

The physics solvers employed for neural network training are primarily iterative, and hence, differentiating through them introduces a severe computational burden as iterations grow large. Inspired by works in bilevel optimization, we show that full accuracy of the network is achievable through physics significantly coarser than fully converged solvers. We propose Progressively Refined Differentiable Physics (PRDP), an approach that identifies the level of physics refinement sufficient for full training accuracy. By beginning with coarse physics, adaptively refining it during training, and stopping refinement at the level adequate for training, it enables significant compute savings without sacrificing network accuracy. Our focus is on differentiating iterative linear solvers for sparsely discretized differential operators, which are fundamental to scientific computing. PRDP is applicable to both unrolled and implicit differentiation. We validate its performance on a variety of learning scenarios involving differentiable physics solvers such as inverse problems, autoregressive neural emulators, and correction-based neural-hybrid solvers. In the challenging example of emulating the Navier-Stokes equations, we reduce training time by 62%.

arXiv:2502.19597공식 코드 · Papers with Code

Introduction to Sequence Modeling with Transformers

Understanding the transformer architecture and its workings is essential for machine learning (ML) engineers. However, truly understanding the transformer architecture can be demanding, even if you have a solid background in machine learning or deep learning. The main working horse is attention, which yields to the transformer encoder-decoder structure. However, putting attention aside leaves several programming components that are easy to implement but whose role for the whole is unclear. These components are 'tokenization', 'embedding' ('un-embedding'), 'masking', 'positional encoding', and 'padding'. The focus of this work is on understanding them. To keep things simple, the understanding is built incrementally by adding components one by one, and after each step investigating what is doable and what is undoable with the current model. Simple sequences of zeros (0) and ones (1) are used to study the workings of each step.

arXiv:2502.19551공식 코드 · Papers with Code

Extremely Greedy Equivalence Search

The goal of causal discovery is to learn a directed acyclic graph from data. One of the most well-known methods for this problem is Greedy Equivalence Search (GES). GES searches for the graph by incrementally and greedily adding or removing edges to maximize a model selection criterion. It has strong theoretical guarantees on infinite data but can fail in practice on finite data. In this paper, we first identify some of the causes of GES's failure, finding that it can get blocked in local optima, especially in denser graphs. We then propose eXtremely Greedy Equivalent Search (XGES), which involves a new heuristic to improve the search strategy of GES while retaining its theoretical guarantees. In particular, XGES favors deleting edges early in the search over inserting edges, which reduces the possibility of the search ending in local optima. A further contribution of this work is an efficient algorithmic formulation of XGES (and GES). We benchmark XGES on simulated datasets with known ground truth. We find that XGES consistently outperforms GES in recovering the correct graphs, and it is 10 times faster. XGES implementations in Python and C++ are available at https://github.com/ANazaret/XGES.

arXiv:2502.19512공식 코드 · Papers with Code

TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs

Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in inductive settings. Empirically, we show that TRIX outperforms the state-of-the-art fully inductive models in zero-shot entity and relation predictions in new domains, and outperforms large-context LLMs in out-of-domain predictions. The source code is available at https://github.com/yuchengz99/TRIX.

arXiv:2502.19502공식 코드 · Papers with Code

Models That Are Interpretable But Not Transparent

Faithful explanations are essential for machine learning models in high-stakes applications. Inherently interpretable models are well-suited for these applications because they naturally provide faithful explanations by revealing their decision logic. However, model designers often need to keep these models proprietary to maintain their value. This creates a tension: we need models that are interpretable--allowing human decision-makers to understand and justify predictions, but not transparent, so that the model's decision boundary is not easily replicated by attackers. Shielding the model's decision boundary is particularly challenging alongside the requirement of completely faithful explanations, since such explanations reveal the true logic of the model for an entire subspace around each query point. This work provides an approach, FaithfulDefense, that creates model explanations for logical models that are completely faithful, yet reveal as little as possible about the decision boundary. FaithfulDefense is based on a maximum set cover formulation, and we provide multiple formulations for it, taking advantage of submodularity.

arXiv:2502.19361공식 코드 · Papers with Code

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

Recently, o1-like models have drawn significant attention, where these models produce the long Chain-of-Thought (CoT) reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs). In this paper, to understand the qualities of these long CoTs and measure the critique abilities of existing LLMs on these long CoTs, we introduce the DeltaBench, including the generated long CoTs from different o1-like models (e.g., QwQ, DeepSeek-R1) for different reasoning tasks (e.g., Math, Code, General Reasoning), to measure the ability to detect errors in long CoT reasoning. Based on DeltaBench, we first perform fine-grained analysis of the generated long CoTs to discover the effectiveness and efficiency of different o1-like models. Then, we conduct extensive evaluations of existing process reward models (PRMs) and critic models to detect the errors of each annotated process, which aims to investigate the boundaries and limitations of existing PRMs and critic models. Finally, we hope that DeltaBench could guide developers to better understand the long CoT reasoning abilities of their models.

arXiv:2502.15132공식 코드 · Papers with Code

CoT-ICL Lab: A Petri Dish for Studying Chain-of-Thought Learning from In-Context Demonstrations

We introduce CoT-ICL Lab, a framework and methodology to generate synthetic tokenized datasets and systematically study chain-of-thought (CoT) in-context learning (ICL) in language models. CoT-ICL Lab allows fine grained control over the complexity of in-context examples by decoupling (1) the causal structure involved in chain token generation from (2) the underlying token processing functions. We train decoder-only transformers (up to 700M parameters) on these datasets and show that CoT accelerates the accuracy transition to higher values across model sizes. In particular, we find that model depth is crucial for leveraging CoT with limited in-context examples, while more examples help shallow models match deeper model performance. Additionally, limiting the diversity of token processing functions throughout training improves causal structure learning via ICL. We also interpret these transitions by analyzing transformer embeddings and attention maps. Overall, CoT-ICL Lab serves as a simple yet powerful testbed for theoretical and empirical insights into ICL and CoT in language models.

arXiv:2502.20286공식 코드 · Papers with Code

Multiple Linked Tensor Factorization

In biomedical research and other fields, it is now common to generate high content data that are both multi-source and multi-way. Multi-source data are collected from different high-throughput technologies while multi-way data are collected over multiple dimensions, yielding multiple tensor arrays. Integrative analysis of these data sets is needed, e.g., to capture and synthesize different facets of complex biological systems. However, despite growing interest in multi-source and multi-way factorization techniques, methods that can handle data that are both multi-source and multi-way are limited. In this work, we propose a Multiple Linked Tensors Factorization (MULTIFAC) method extending the CANDECOMP/PARAFAC (CP) decomposition to simultaneously reduce the dimension of multiple multi-way arrays and approximate underlying signal. We first introduce a version of the CP factorization with L2 penalties on the latent factors, leading to rank sparsity. When extended to multiple linked tensors, the method automatically reveals latent components that are shared across data sources or individual to each data source. We also extend the decomposition algorithm to its expectation-maximization (EM) version to handle incomplete data with imputation. Extensive simulation studies are conducted to demonstrate MULTIFAC's ability to (i) approximate underlying signal, (ii) identify shared and unshared structures, and (iii) impute missing data. The approach yields an interpretable decomposition on multi-way multi-omics data for a study on early-life iron deficiency.

arXiv:2502.20275공식 코드 · Papers with Code

How cancer emerges: Data-driven universal insights into tumorigenesis via hallmark networks

Cancer is a complex disease driven by dynamic regulatory shifts that cannot be fully captured by individual molecular profiling. We employ a data-driven approach to construct a coarse-grained dynamic network model based on hallmark interactions, integrating stochastic differential equations with gene regulatory network data to explore key macroscopic dynamic changes in tumorigenesis. Our analysis reveals that network topology undergoes significant reconfiguration before hallmark expression shifts, serving as an early indicator of malignancy. A pan-cancer examination across $15$ cancer types uncovers universal patterns, where Tissue Invasion and Metastasis exhibits the most significant difference between normal and cancer states, while the differences in Reprogramming Energy Metabolism are the least pronounced, consistent with the characteristic features of tumor biology. These findings reinforce the systemic nature of cancer evolution, highlighting the potential of network-based systems biology methods for understanding critical transitions in tumorigenesis.

arXiv:2502.20122공식 코드 · Papers with Code

Self-Training Elicits Concise Reasoning in Large Language Models

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens, incurring extraneous inference costs. Upon examination of the output distribution of current LLMs, we find evidence on their latent ability to reason more concisely, relative to their default behavior. To elicit this capability, we propose simple fine-tuning methods which leverage self-generated concise reasoning paths obtained by best-of-N sampling and few-shot conditioning, in task-specific settings. Our combined method achieves a 30% reduction in output tokens on average, across five model families on GSM8K and MATH, while maintaining average accuracy. By exploiting the fundamental stochasticity and in-context learning capabilities of LLMs, our self-training approach robustly elicits concise reasoning on a wide range of models, including those with extensive post-training. Code is available at https://github.com/TergelMunkhbat/concise-reasoning