Despite the remarkable success of Large Language Models (LLMs), evaluating their outputs' quality regarding preference remains a critical challenge. While existing works usually leverage a strong LLM as the judge for comparing LLMs' response pairwisely, such a single-evaluator approach is vulnerable to cyclic preference, i.e., output A is better than B, B than C, but C is better than A, causing contradictory evaluation results. To address this, we introduce PGED (Preference Graph Ensemble and Denoise), a novel approach that leverages multiple model-based evaluators to construct preference graphs, and then ensembles and denoises these graphs for acyclic, non-contradictory evaluation results. We provide theoretical guarantees for our framework, demonstrating its efficacy in recovering the ground truth preference structure. Extensive experiments on ten benchmarks demonstrate PGED 's superiority in three applications: 1) model ranking for evaluation, 2) response selection for test-time scaling, and 3) data selection for model fine-tuning. Notably, PGED combines small LLM evaluators (e.g., Llama3-8B, Mistral-7B, Qwen2-7B) to outperform strong ones (e.g., Qwen2-72B), showcasing its effectiveness in enhancing evaluation reliability and improving model performance.

Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Machine learning tasks over image databases often generate masks that annotate image content (e.g., saliency maps, segmentation maps, depth maps) and enable a variety of applications (e.g., determine whether a model is learning spurious correlations or if an image was maliciously modified to mislead a model). While queries that retrieve examples based on mask properties are valuable to practitioners, existing systems do not support them efficiently. In this paper, we formalize the problem and propose MaskSearch, a system that focuses on accelerating queries over databases of image masks while guaranteeing the query result accuracy. MaskSearch leverages a novel indexing technique and an efficient filter-verification query execution framework. Experiments with our prototype show that MaskSearch, using indexes approximately 5% of the compressed data size, accelerates individual queries by up to two orders of magnitude and consistently outperforms existing methods on various multi-query workloads that simulate dataset exploration and analysis processes.

Failure attribution in LLM multi-agent systems—identifying the agent and step responsible for task failures—provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate a new research area: automated failure attribution for LLM multi-agent systems. To support this initiative, we introduce the Who&When dataset, comprising extensive failure logs from 127 LLM multi-agent systems with fine-grained annotations linking failures to specific agents and decisive error steps. Using the Who&When, we develop and evaluate three automated failure attribution methods, summarizing their corresponding pros and cons. The best method achieves 53.5% accuracy in identifying failure-responsible agents but only 14.2% in pinpointing failure steps, with some methods performing below random. Even SOTA reasoning models, such as OpenAI o1 and DeepSeek R1, fail to achieve practical usability. These results highlight the task’s complexity and the need for further research in this area. Code and dataset are available in https://github.com/mingyin1/Agents_Failure_Attribution.

Constructing accurate digital twins of articulated objects is essential for robotic simulation training and embodied AI world model building, yet historically requires painstaking manual modeling or multi-stage pipelines. In this work, we propose \textbf{URDF-Anything}, an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM). URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction. It implements a specialized [SEG] token mechanism that interacts directly with point cloud features, enabling fine-grained part-level segmentation while maintaining consistency with the kinematic parameter predictions. Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches regarding geometric segmentation (mIoU 17\% improvement), kinematic parameter prediction (average error reduction of 29\%), and physical executability (surpassing baselines by 50\%). Notably, our method exhibits excellent generalization ability, performing well even on objects outside the training set. This work provides an efficient solution for constructing digital twins for robotic simulation, significantly enhancing the sim-to-real transfer capability.

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, recent investigations find that most-if not all-our state-of-the-art vision-language models struggle at compositionality. They are unable to distinguish between images of “a girl in white facing a man in black” and “a girl in blackfacing a man in white”. More-over, prior work suggests that compositionality doesn't arise with scale: larger model sizes or training data don't help. This paper develops a new iterated training algorithm that incentivizes compositionality. We draw on decades of cognitive science research that identifies cultural transmission-the need to teach a new generation-as a necessary inductive prior that incentivizes humans to develop compositional languages. Specifically, we reframe vision-language contrastive learning as the Lewis Signaling Game between a vision agent and a language agent, and ope rationalize cultural transmission by iteratively resetting one of the agent's weights during training. After every iteration, this training paradigm induces representations that become “easier to learn”, a property of compositional languages: e.g. our model trained on CC3M and CC12M improves standard CLIP by 4.7%, 4.0% respectfully in the SugarCrepe benchmark.

Clinicians often rely on data engineers to retrieve complex patient information from electronic health record (EHR) systems, a process that is both inefficient and time-consuming. We propose EHRAgent, a large language model (LLM) agent empowered with accumulative domain knowledge and robust coding capability. EHRAgent enables autonomous code generation and execution to facilitate clinicians in directly interacting with EHRs using natural language. Specifically, we formulate a multi-tabular reasoning task based on EHRs as a tool-use planning process, efficiently decomposing a complex task into a sequence of manageable actions with external toolsets. We first inject relevant medical information to enable EHRAgent to effectively reason about the given query, identifying and extracting the required records from the appropriate tables. By integrating interactive coding and execution feedback, EHRAgent then effectively learns from error messages and iteratively improves its originally generated code. Experiments on three real-world EHR datasets show that EHRAgent outperforms the strongest baseline by up to 29.6% in success rate, verifying its strong capacity to tackle complex clinical tasks with minimal demonstrations.

Most existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43.22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.

Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as *agents*, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we present a novel paradigm of training LLM agents without modifying the LLM weights, which is particularly useful when the LLMs are difficult or inaccessible for modifications. Inspired by how humans continuously forge tools to adapt to real-world tasks, rather than change our biological structure to fit a static set of tools, we propose to progressively forge agent's functions to better solve the downstream tasks instead of modifying the LLM weights. By treating the functions as learnable `agent parameters' and leveraging the fundamental idea of model training in artificial intelligence, we develop AgentOptimizer that employs the LLM to update agents' functions and devise an *agent training* algorithm with two strategies, roll-back, and early-stop, to streamline the training process. With extensive experiments, we showcase that the agent training paradigm could significantly improve the performance of representative LLM agents in various downstream tasks. We also study the behavior of the agent training regarding aspects like the learning curve and domain transferability.

Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets. While existing works have explored curating such datasets automatically, the resultant datasets are not explicitly aligned with domain expertise. In this work, we propose a data-centric framework, Biomedical Visual Instruction Tuning with Clinician Preference Alignment (BioMed-VITAL), that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models. First, during the generation stage, we prompt the GPT-4V generator with a diverse set of clinician-selected demonstrations for preference-aligned data candidate generation. Then, during the selection phase, we train a separate selection model, which explicitly distills clinician and policy-guided model preferences into a rating function to select high-quality data for medical instruction tuning. Results show that the model tuned with the instruction-following data from our method demonstrates a significant improvement in open visual chat (18.5% relatively) and medical VQA (win rate up to 81.73%). Our instruction-following data and models are available at https://BioMed-VITAL.github.io.

We introduce DataComp for Language Models, a testbed for controlled dataset experiments with the goal of improving language models.As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretraining recipes based on the OpenLM framework, and a broad suite of 53 downstream evaluations.Participants in the DCLM benchmark can experiment with data curation strategies such as deduplication, filtering, and data mixing atmodel scales ranging from 412M to 7B parameters.As a baseline for DCLM, we conduct extensive experiments and find that model-based filtering is key to assembling a high-quality training set.The resulting dataset, DCLM-Baseline, enables training a 7B parameter language model from scratch to 63% 5-shot accuracy on MMLU with 2T training tokens.Compared to MAP-Neo, the previous state-of-the-art in open-data language models, DCLM-Baseline represents a 6 percentage point improvement on MMLU while being trained with half the compute.Our results highlight the importance of dataset design for training language models and offer a starting point for further research on data curation. We release the \dclm benchmark, framework, models, and datasets at https://www.datacomp.ai/dclm/

Benchmarks for large multimodal language models (MLMs) now serve to simultaneously assess the general capabilities of models instead of evaluating for a specific capability. As a result, when a developer wants to identify which models to use for their application, they are overwhelmed by the number of benchmarks and remain uncertain about which benchmark's results are most reflective of their specific use case. This paper introduces Task-Me-Anything, a benchmark generation engine which produces a benchmark tailored to a user's needs. Task-Me-Anything maintains an extendable taxonomy of visual assets and can programmatically generate a vast number of task instances. Additionally, it algorithmically addresses user queries regarding MLM performance efficiently within a computational budget. It contains 113K images, 10K videos, 2K 3D object assets, over 365 object categories, 655 attributes, and 335 relationships. It can generate 500M image/video question-answering pairs, which focus on evaluating MLM perceptual capabilities. Task-Me-Anything reveals critical insights: open-source MLMs excel in object and attribute recognition but lack spatial and temporal understanding; each model exhibits unique strengths and weaknesses; larger models generally perform better, though exceptions exist; and GPT4O demonstrates challenges in recognizing rotating/moving objects and distinguishing colors.

We present PATRON, a prompt-based data selection method for pre-trained language model fine-tuning under cold-start scenarios, i.e., no initial labeled data are available. In PATRON, we design (1) a prompt-based uncertainty propagation approach to estimate the importance of data points and (2) a partition-then-rewrite (PTR) strategy to promote sample diversity when querying for annotations. Experiments on six text classification datasets show that PATRON outperforms the strongest cold-start data selection baselines by up to 6.9%. Besides, with 128 labels only, PATRON achieves 91.0% and 92.1% of the fully supervised performance based on vanilla fine-tuning and prompt-based learning respectively. Our implementation of PATRON will be published upon acceptance.

Programmatic Weak Supervision (PWS) has emerged as a widespread paradigm to synthesize training labels efficiently. The core component of PWS is the label model, which infers true labels by aggregating the outputs of multiple noisy supervision sources abstracted as labeling functions (LFs). Existing statistical label models typically rely only on the outputs of LF, ignoring the instance features when modeling the underlying generative process. In this paper, we attempt to incorporate the instance features into a statistical label model via the proposed FABLE. In particular, it is built on a mixture of Bayesian label models, each corresponding to a global pattern of correlation, and the coefficients of the mixture components are predicted by a Gaussian Process classifier based on instance features. We adopt an auxiliary variable-based variational inference algorithm to tackle the non-conjugate issue between the Gaussian Process and Bayesian label models. Extensive empirical comparison on eleven benchmark datasets sees FABLE achieving the highest averaged performance across nine baselines. Our implementation of FABLE can be found in https://github.com/JieyuZ2/wrench/blob/main/wrench/labelmodel/fable.py.

Prompted weak supervision (PromptedWS) applies pre-trained large language models (LLMs) as the basis for labeling functions (LFs) in a weak supervision framework to obtain large labeled datasets. We further extend the use of LLMs in the loop to address one of the key challenges in weak supervision: learning the statistical dependency structure among supervision sources. In this work, we ask the LLM how similar are these prompted LFs. We propose a Structure Refining Module, a simple yet effective first approach based on the similarities of the prompts by taking advantage of the intrinsic structure in the embedding space. At the core of Structure Refining Module are Labeling Function Removal (LaRe) and Correlation Structure Generation (CosGen). Compared to previous methods that learn the dependencies from weak labels, our method finds the dependencies which are intrinsic to the LFs and less dependent on the data. We show that our Structure Refining Module improves the PromptedWS pipeline by up to 12.7 points on the benchmark tasks. We also explore the trade-offs between efficiency and performance with comprehensive ablation experiments and analysis. Code for this project can be found in https://github.com/BatsResearch/su-bigdata23-code.

Deep reinforcement learning (DRL) gives the promise that an agent learns good policy from high-dimensional information, whereas representation learning removes irrelevant and redundant information and retains pertinent information. In this work, we demonstrate that the learned representation of the Q-network and its target Q-network should, in theory, satisfy a favorable distinguishable representation property. Specifically, there exists an upper bound on the representation similarity of the value functions of two adjacent time steps in a typical DRL setting. However, through illustrative experiments, we show that the learned DRL agent may violate this property and lead to a sub-optimal policy. Therefore, we propose a simple yet effective regularizer called P_olicy E_valuation with E_asy Regularization on Representation (PEER), which aims to maintain the distinguishable representation property via explicit regularization on internal representations. And we provide the convergence rate guarantee of PEER. Implementing PEER requires only one line of code. Our experiments demonstrate that incorporating PEER into DRL can significantly improve performance and sample efficiency. Comprehensive experiments show that PEER achieves state-of-the-art performance on all 4 environments on PyBullet, 9 out of 12 tasks on DM-Control, and 19 out of 26 games on Atari. To the best of our knowledge, PEER is the first work to study the inherent representation property of Q-network and its target. Our code is available at https://sites.google.com/view/peer-cvpr2023/.

Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. Existing methods such as data reweighing, resampling, and supervised contrastive learning enforce the class balance with a price of introducing imbalance between instances of head class and tail class, which may ignore the underlying rich semantic substructures of the former and exaggerate the biases in the latter. We overcome these drawbacks by a novel "subclass-balancing contrastive learning (SBCL)" approach that clusters each head class into multiple subclasses of similar sizes as the tail classes and enforce representations to capture the two-layer class hierarchy between the original classes and their subclasses. Since the clustering is conducted in the representation space and updated during the course of training, the subclass labels preserve the semantic substructures of head classes. Meanwhile, it does not overemphasize tail class samples, so each individual instance contribute to the representation learning equally. Hence, our method achieves both the instance- and subclass-balance, while the original class labels are also learned through contrastive learning among subclasses from different classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance. In addition, we present extensive analyses and ablation studies of SBCL to verify its advantages. Our code is available at https://github.com/JackHck/subclass-balancing-contrastive-learning.

Data augmentation (DA) is widely used to improve the generalization of neural networks by enforcing the invariances and symmetries to pre-defined transformations applied to input data. However, a fixed augmentation policy may have different effects on each sample in different training stages but existing approaches cannot adjust the policy to be adaptive to each sample and the training model. In this paper, we propose "Model-Adaptive Data Augmentation (MADAug)" that jointly trains an augmentation policy network to teach the model "when to learn what". Unlike previous work, MADAug selects augmentation operators for each input image by a model-adaptive policy varying between training stages, producing a data augmentation curriculum optimized for better generalization. In MADAug, we train the policy through a bi-level optimization scheme, which aims to minimize a validation-set loss of a model trained using the policy-produced data augmentations. We conduct an extensive evaluation of MADAug on multiple image classification tasks and network architectures with thorough comparisons to existing DA approaches. MADAug outperforms or is on par with other baselines and exhibits better fairness: it brings improvement to all classes and more to the difficult ones. Moreover, MADAug learned policy shows better performance when transferred to fine-grained datasets. In addition, the auto-optimized policy in MADAug gradually introduces increasing perturbations and naturally forms an easy-to-hard curriculum. Our code is available at https://github.com/JackHck/MADAug.

Traditional methods of pre-training, fine-tuning, and ensembling often overlook essential relational data and task interconnections. To address this gap, our study presents a novel approach to harnessing this relational information via a relational graph-based model. We introduce Relational grAph Model ensemBLE model, abbreviated as RAMBLE. This model distinguishes itself by performing class label inference simultaneously across all data nodes and task nodes, employing the relational graph in a transductive manner. This fine-grained approach allows us to better comprehend and model the intricate interplay between data and tasks. Furthermore, we incorporate a novel variational information bottleneck-guided scheme for embedding fusion and aggregation. This innovative technique facilitates the creation of an informative fusion embedding, honing in on embeddings beneficial for the intended task while simultaneously filtering out potential noise-laden embeddings. Our theoretical analysis, grounded in information theory, confirms that the use of relational information for embedding fusion allows us to achieve higher upper and lower bounds on our target task's accuracy. We thoroughly assess our proposed model across eight diverse datasets, and the experimental results demonstrate the model's effective utilization of relational knowledge derived from all pre-trained models, thereby enhancing its performance on our target tasks.

Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design. While there has been a surge of interest in advancing model-centric techniques, the influence of both data quantity and quality on molecular representations is not yet clearly understood within this field. In this paper, we delve into the neural scaling behaviors of MRL from a data-centric viewpoint, examining four key dimensions: (1) data modalities, (2) dataset splitting, (3) the role of pre-training, and (4) model capacity.Our empirical studies confirm a consistent power-law relationship between data volume and MRL performance across these dimensions. Additionally, through detailed analysis, we identify potential avenues for improving learning efficiency.To challenge these scaling laws, we adapt seven popular data pruning strategies to molecular data and benchmark their performance. Our findings underline the importance of data-centric MRL and highlight possible directions for future research.

Multimodal datasets are a critical component in recent breakthroughs such as CLIP, Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the machine learning ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the resulting model on 38 downstream test sets. Our benchmark consists of multiple compute scales spanning four orders of magnitude, which enables the study of scaling trends and makes the benchmark accessible to researchers with varying resources. Our baseline experiments show that the DataComp workflow leads to better training sets. Our best baseline, DataComp-1B, enables training a CLIP ViT-L/14 from scratch to 79.2% zero-shot accuracy on ImageNet, outperforming OpenAI's CLIP ViT-L/14 by 3.7 percentage points while using the same training procedure and compute. We release \datanet and all accompanying code at www.datacomp.ai.

In the last year alone, a surge of new benchmarks to measure $\textit{compositional}$ understanding of vision-language models have permeated the machine learning ecosystem.Given an image, these benchmarks probe a model's ability to identify its associated caption amongst a set of compositional distractors.Surprisingly, we find significant biases in $\textit{all}$ these benchmarks rendering them hackable. This hackability is so dire that blind models with no access to the image outperform state-of-the-art vision-language models.To remedy this rampant vulnerability, we introduce $\textit{SugarCrepe}$, a new benchmark for vision-language compositionality evaluation.We employ large language models, instead of rule-based templates used in previous benchmarks, to generate fluent and sensical hard negatives, and utilize an adversarial refinement mechanism to maximally reduce biases. We re-evaluate state-of-the-art models and recently proposed compositionality inducing strategies, and find that their improvements were hugely overestimated, suggesting that more innovation is needed in this important direction.We release $\textit{SugarCrepe}$ and the code for evaluation at: https://github.com/RAIVNLab/sugar-crepe.

Labeling training data is a critical and expensive step in producing high accuracy ML models, whether training from scratch or fine-tuning. To make labeling more efficient, two major approaches are programmatic weak supervision (WS) and semi-supervised learning (SSL). More recent works have either explicitly or implicitly used techniques at their intersection, but in various complex and ad hoc ways. In this work, we define a simple, modular design space to study the use of SSL techniques for WS more systematically. Surprisingly, we find that fairly simple methods from our design space match the performance of more complex state-of-the-art methods, averaging a 3 p.p. increase in accuracy/F1-score across 8 standard WS benchmarks. Further, we provide practical guidance on when different components are worth their added complexity and training costs. Contrary to current understanding, we find using SSL is not necessary to obtain the best performance on most WS benchmarks but is more effective when: (1) end models are smaller, and (2) WS provides labels for only a small portion of training examples.

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e.g., specifying attributes like length and style), which have the potential to yield diverse and attributed generated data. Our investigation focuses on datasets with high cardinality and diverse domains, wherein we demonstrate that attributed prompts outperform simple class-conditional prompts in terms of the resulting model's performance. Additionally, we present a comprehensive empirical study on data generation encompassing vital aspects like bias, diversity, and efficiency, and highlight three key observations: firstly, synthetic datasets generated by simple prompts exhibit significant biases, such as regional bias; secondly, attribute diversity plays a pivotal role in enhancing model performance; lastly, attributed prompts achieve the performance of simple class-conditional prompts while utilizing only 5\% of the querying cost of ChatGPT associated with the latter. The data and code are available on {\url{https://github.com/yueyu1030/AttrPrompt}}.

Pre-training datasets are critical for building state-of-the-art machine learning models, motivating rigorous study on their impact on downstream tasks. In this work, we study the impact of the trade-off between the intra-class diversity (the number of samples per class) and the inter-class diversity (the number of classes) of a supervised pre-training dataset. Empirically, we found that with the size of the pre-training dataset fixed, the best downstream performance comes with a balance on the intra-/inter-class diversity. To understand the underlying mechanism, we show theoretically that the downstream performance depends monotonically on both types of diversity. Notably, our theory reveals that the optimal class-to-sample ratio (#classes / #samples per class) is invariant to the size of the pre-training dataset, which motivates an application of predicting the optimal number of pre-training classes. We demonstrate the effectiveness of this application by an improvement of around 2 points on the downstream tasks when using ImageNet as the pre-training dataset.

Session-based recommendation (SBR), which makes the next-item recommendation based on previous anonymous actions, has drawn increasing attention. The last decade has seen multiple deep learning-based modeling choices applied on SBR successfully, e.g., recurrent neural networks (RNNs), convolutional neural networks (CNNs), graph neural networks (GNNs), and each modeling choice has its intrinsic superiority and limitation. We argue that these modeling choices differentiate from each other by (1) the way they capture the interactions between items within a session and (2) the operators they adopt for composing the neural network, e.g., convolutional operator or self-attention operator.

To create a large amount of training labels for machine learning models effectively and efficiently, researchers have turned to Weak Supervision (WS), which uses programmatic labeling sources rather than manual annotation. Existing works of WS for binary classification typically assume the presence of labeling sources that are able to assign both positive and negative labels to data in roughly balanced proportions. However, for many tasks of interest where there is a minority positive class, negative examples could be too diverse for developers to generate indicative labeling sources. Thus, in this work, we study the application of WS on binary classification tasks with positive labeling sources only. We propose WEAPO, a simple yet competitive WS method for producing training labels without negative labeling sources. On 10 benchmark datasets, we show WEAPO achieves the highest averaged performance in terms of both the quality of synthesized labels and the performance of the final classifier supervised with these labels. We incorporated the implementation of WEAPO into WRENCH, an existing benchmarking platform.

Yue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, Chao Zhang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Programmatic Weak Supervision (PWS) aggregates the source votes of multiple weak supervision sources into probabilistic training labels, which are in turn used to train an end model. With its increasing popularity, it is critical to have some tool for users to understand the influence of each component (\eg, the source vote or training data) in the pipeline and interpret the end model behavior. To achieve this, we build on Influence Function (IF) and propose source-aware IF, which leverages the generation process of the probabilistic labels to decompose the end model's training objective and then calculate the influence associated with each (data, source, class) tuple. These primitive influence score can then be used to estimate the influence of individual component of PWS, such as source vote, supervision source, and training data. On datasets of diverse domains, we demonstrate multiple use cases: (1) interpreting incorrect predictions from multiple angles that reveals insights for debugging the PWS pipeline, (2) identifying mislabeling of sources with a gain of 9\%-37\% over baselines, and (3) improving the end model's generalization performance by removing harmful components in the training objective (13\%-24\% better than ordinary IF).

Taxonomies are fundamental to many real-world applications in various domains, serving as structural representations of knowledge. To deal with the increasing volume of new concepts needed to be organized as taxonomies, researchers turn to automatically completion of an existing taxonomy with new concepts. In this paper, we propose TaxoEnrich, a new taxonomy completion framework, which effectively leverages both semantic features and structural information in the existing taxonomy and offers a better representation of candidate position to boost the performance of taxonomy completion. Specifically, TaxoEnrichconsists of four components: (1) taxonomy-contextualized embedding which incorporates both semantic meanings of concept and taxonomic relations based on powerful pretrained language models; (2) a taxonomy-aware sequential encoder which learns candidate position representations by encoding the structural information of taxonomy; (3) a query-aware sibling encoder which adaptively aggregates candidate siblings to augment candidate position representations based on their importance to the query-position matching; (4) a query-position matching model which extends existing work with our new candidate position representations. Extensive experiments on four large real-world datasets from different domains show that TaxoEnrichachieves the best performance among all evaluation metrics and outperforms previous state-of-the-art methods by a large margin.

Weak Supervision (WS) techniques allow users to efficiently create large training datasets by programmatically labeling data with heuristic sources of supervision. While the success of WS relies heavily on the provided labeling heuristics, the process of how these heuristics are created in practice has remained under-explored. In this work, we formalize the development process of labeling heuristics as an interactive procedure, built around the existing workflow where users draw ideas from a selected set of development data for designing the heuristic sources. With the formalism, shown in Figure 1, we study two core problems of (1) how to strategically select the development data to guide users in efficiently creating informative heuristics, and (2) how to exploit the information within the development process to contextualize and better learn from the resultant heuristics. Building upon two novel methodologies that effectively tackle the respective problems considered, we present Nemo, an end-to-end interactive system that improves the overall productivity of WS learning pipeline by an average 20% (and up to 47% in one task) compared to the prevailing WS approach.

Automatically constructing taxonomy finds many applications in e-commerce and web search. One critical challenge is as data and business scope grow in real applications, new concepts are emerging and needed to be added to the existing taxonomy. Previous approaches focus on the taxonomy expansion, i.e. finding an appropriate hypernym concept from the taxonomy for a new query concept. In this paper, we formulate a new task, “taxonomy completion”, by discovering both the hypernym and hyponym concepts for a query. We propose Triplet Matching Network (TMN), to find the appropriate pairs for a given query concept. TMN consists of one primal scorer and multiple auxiliary scorers. These auxiliary scorers capture various fine-grained signals (e.g., query to hypernym or query to hyponym semantics), and the primal scorer makes a holistic prediction on triplet based on the internal feature representations of all auxiliary scorers. Also, an innovative channel-wise gating mechanism that retains task-specific information in concept representations is introduced to further boost model performance. Experiments on four real-world large-scale datasets show that TMN achieves the best performance on both taxonomy completion task and the previous taxonomy expansion task, outperforming existing methods.

Network representation learning aims at transferring node proximity in networks into distributed vectors, which can be leveraged in various downstream applications. Recent research has shown that nodes in a network can often be organized in latent hierarchical structures, but without a particular underlying taxonomy, the learned node embedding is less useful nor interpretable. In this work, we aim to improve network embedding by modeling the conditional node proximity in networks indicated by node labels residing in real taxonomies. In the meantime, we also aim to model the hierarchical label proximity in the given taxonomies, which is too coarse by solely looking at the hierarchical topologies. Comprehensive experiments and case studies demonstrate the utility of TAXOGAN.

Network embedding aims at transferring node proximity in networks into distributed vectors, which can be leveraged in various downstream applications. Recent research has shown that nodes in a network can often be organized in latent hierarchical structures, but without a particular underlying taxonomy, the learned node embedding is less useful nor interpretable. In this work, we aim to improve network embedding by modeling the conditional node proximity in networks indicated by node labels residing in real taxonomies. In the meantime, we also aim to model the hierarchical label proximity in the given taxonomies, which is too coarse by solely looking at the hierarchical topologies. To this end, we propose TaxoGAN to co-embed network nodes and hierarchical labels, through a hierarchical network generation process. Particularly, TaxoGAN models the child labels and network nodes of each parent label in an individual embedding space while learning to transfer network proximity among the spaces of hierarchical labels through stacked network generators and embedding encoders. To enable robust and efficient model inference, we further develop a hierarchical adversarial training process. Comprehensive experiments and case studies on four real-world datasets of networks with hierarchical labels demonstrate the utility of TaxoGAN in improving network embedding on traditional tasks of node classification and link prediction, as well as novel tasks like conditional proximity search and fine-grained taxonomy layout.

Concept maps provide concise structured representations for documents regarding their important concepts and interaction links, which have been widely used for document summarization and downstream tasks. However, the construction of concept maps often relies heavily on heuristic design and auxiliary tools. Recent popular neural network models, on the other hand, are shown effective in tasks across various domains, but are short in interpretability and prone to overfitting. In this work, we bridge the gap between concept map construction and neural network models, by designing doc2graph, a novel weakly-supervised text-to-graph neural network, which generates concept maps in the middle and is trained towards document-level tasks like document classification. In our experiments, doc2graph outperforms both its traditional baselines and neural counterparts by significant margins in document classification, while producing high-quality interpretable concept maps as document structured summarization.

While node semantics have been extensively explored in social networks, little research attention has been paid to pro le edge semantics, i.e., social relations. Ideal edge semantics should not only show that two users are connected, but also why they know each other and what they share in common. However, relations in social networks are often hard to pro le, due to noisy multi-modal signals and limited user-generated ground-truth labels.

Classification is one of the most important problems in machine learning. To address label scarcity, semi-supervised learning (SSL) has been intensively studied over the past two decades, which mainly leverages data affinity modeled by networks. Label propagation (LP), however, as the most popular SSL technique, mostly only works on homogeneous networks with single-typed simple interactions. In this work, we focus on the more general and powerful heterogeneous networks, which accommodate multi-typed objects and links, and thus endure multi-typed complex interactions. Specifically, we propose neural embedding propagation (NEP), which leverages distributed embeddings to represent objects and dynamically composed modular networks to model their complex interactions. While generalizing LP as a simple instance, NEP is far more powerful in its natural awareness of different types of objects and links, and the ability to automatically capture their important interaction patterns. Further, we develop a series of efficient training strategies for NEP, leading to its easy deployment on real-world heterogeneous networks with millions of objects. With extensive experiments on three datasets, we comprehensively demonstrate the effectiveness, efficiency, and robustness of NEP compared with state-of-the-art network embedding and SSL algorithms.