Hoang Thanh Lam

Gabriele Picco, Marcos Martínez Galindo, Alberto Purpura et al. · ibm-research

The Zero-Shot Learning (ZSL) task pertains to the identification of entities or relations in texts that were not seen during training. ZSL has emerged as a critical research area due to the scarcity of labeled data in specific domains, and its applications have grown significantly in recent years. With the advent of large pretrained language models, several novel methods have been proposed, resulting in substantial improvements in ZSL performance. There is a growing demand, both in the research community and industry, for a comprehensive ZSL framework that facilitates the development and accessibility of the latest methods and pretrained models.In this study, we propose a novel ZSL framework called Zshot that aims to address the aforementioned challenges. Our primary objective is to provide a platform that allows researchers to compare different state-of-the-art ZSL methods with standard benchmark datasets. Additionally, we have designed our framework to support the industry with readily available APIs for production under the standard SpaCy NLP pipeline. Our API is extendible and evaluable, moreover, we include numerous enhancements such as boosting the accuracy with pipeline ensembling and visualization utilities available as a SpaCy extension.

Hoang Thanh Lam, Marco Luca Sbodio, Marcos Martínez Galindo et al.

Recent research on predicting the binding affinity between drug molecules and proteins use representations learned, through unsupervised learning techniques, from large databases of molecule SMILES and protein sequences. While these representations have significantly enhanced the predictions, they are usually based on a limited set of modalities, and they do not exploit available knowledge about existing relations among molecules and proteins. In this study, we demonstrate that by incorporating knowledge graphs from diverse sources and modalities into the sequences or SMILES representation, we can further enrich the representation and achieve state-of-the-art results for drug-target binding affinity prediction in the established Therapeutic Data Commons (TDC) benchmarks. We release a set of multimodal knowledge graphs, integrating data from seven public data sources, and containing over 30 million triples. Our intention is to foster additional research to explore how multimodal knowledge enhanced protein/molecule embeddings can improve prediction tasks, including prediction of binding affinity. We also release some pretrained models learned from our multimodal knowledge graphs, along with source code for running standard benchmark tasks for prediction of biding affinity.

Minh-Dung Dao, Quy Minh Le, Hoang Thanh Lam et al.

With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and brittle applications. Existing efforts to characterise agentic design patterns often lack a rigorous systems-theoretic foundation, resulting in high-level or convenience-based taxonomies that are difficult to implement. This paper addresses this gap by introducing a principled methodology for engineering robust AI agents. We propose two primary contributions: first, a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems: Reasoning & World Model, Perception & Grounding, Action Execution, Learning & Adaptation, and Inter-Agent Communication. Second, derived from this architecture and directly mapped to a comprehensive taxonomy of agentic challenges, we present a collection of 12 agentic design patterns. These patterns - categorised as Foundational, Cognitive & Decisional, Execution & Interaction, and Adaptive & Learning - offer reusable, structural solutions to recurring problems in agent design. The utility of the framework is demonstrated by a case study on the ReAct framework, showing how the proposed patterns can rectify systemic architectural deficiencies. This work provides a foundational language and a structured methodology to standardise agentic design communication among researchers and engineers, leading to more modular, understandable, and reliable autonomous systems.

Quan M. Tran, Suong N. Hoang, Lam M. Nguyen et al.

Foundational models (FMs), pretrained on extensive datasets using self-supervised techniques, are capable of learning generalized patterns from large amounts of data. This reduces the need for extensive labeled datasets for each new task, saving both time and resources by leveraging the broad knowledge base established during pretraining. Most research on FMs has primarily focused on unstructured data, such as text and images, or semi-structured data, like time-series. However, there has been limited attention to structured data, such as tabular data, which, despite its prevalence, remains under-studied due to a lack of clean datasets and insufficient research on the transferability of FMs for various tabular data tasks. In response to this gap, we introduce a framework called TabularFM, which incorporates state-of-the-art methods for developing FMs specifically for tabular data. This includes variations of neural architectures such as GANs, VAEs, and Transformers. We have curated a million of tabular datasets and released cleaned versions to facilitate the development of tabular FMs. We pretrained FMs on this curated data, benchmarked various learning methods on these datasets, and released the pretrained models along with leaderboards for future comparative studies. Our fully open-sourced system provides a comprehensive analysis of the transferability of tabular FMs. By releasing these datasets, pretrained models, and leaderboards, we aim to enhance the validity and usability of tabular FMs in the near future.

Gabriele Picco, Leopold Fuchs, Marcos Martínez Galindo et al.

Zero-shot entity and relation classification models leverage available external information of unseen classes -- e.g., textual descriptions -- to annotate input text data. Thanks to the minimum data requirement, Zero-Shot Learning (ZSL) methods have high value in practice, especially in applications where labeled data is scarce. Even though recent research in ZSL has demonstrated significant results, our analysis reveals that those methods are sensitive to provided textual descriptions of entities (or relations). Even a minor modification of descriptions can lead to a change in the decision boundary between entity (or relation) classes. In this paper, we formally define the problem of identifying effective descriptions for zero shot inference. We propose a strategy for generating variations of an initial description, a heuristic for ranking them and an ensemble method capable of boosting the predictions of zero-shot models through description enhancement. Empirical results on four different entity and relation classification datasets show that our proposed method outperform existing approaches and achieve new SOTA results on these datasets under the ZSL settings. The source code of the proposed solutions and the evaluation framework are open-sourced.

Khiem Le, Sreejata Dey, Marcos Martínez Galindo et al.

Molecular Property Prediction (MPP) is a central task in drug discovery. While Large Language Models (LLMs) show promise as generalist models for MPP, their current performance remains below the threshold for practical adoption. We propose TreeKD, a novel knowledge distillation method that transfers complementary knowledge from tree-based specialist models into LLMs. Our approach trains specialist decision trees on functional group features, then verbalizes their learned predictive rules as natural language to enable rule-augmented context learning. This enables LLMs to leverage structural insights that are difficult to extract from SMILES strings alone. We further introduce rule-consistency, a test-time scaling technique inspired by bagging that ensembles predictions across diverse rules from a Random Forest. Experiments on 22 ADMET properties from the TDC benchmark demonstrate that TreeKD substantially improves LLM performance, narrowing the gap with SOTA specialist models and advancing toward practical generalist models for molecular property prediction.

Quy Minh Le, Minh Sao Khue Luu, Khanh-Tung Tran et al.

Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for coaching tool use in agentic models with flexible reinforcement learning (RL), easing the barriers for researchers and practitioners to adapt LLM-based agents to specific domains. It supports a wide range of training strategies, including RL algorithms such as GRPO and DPO, as well as supervised learning. ToolBrain enables custom reward callables directly on an agent's execution traces or simply utilizes an automated LLM-as-a-judge system for reward generation. It is packed with useful capabilities, including knowledge distillation from large to small models for efficient development, automatic task generation from tool descriptions, seamless tool retrieval, efficient fine-tuning pipelines with QLoRA through Unsloth, and quantized inference via bitsandbytes. We demonstrate ToolBrain through diverse use cases, such as training a CodeAct agent to autonomously execute email search tasks, showing fast, targeted improvements (up to 30.0%) in tool-use skills while keeping the codebase simple and extensible in Agentic AI. Our framework is publicly available at https://toolbrain.org.

Jana Vatter, Mykhaylo Zayats, Marcos Martínez Galindo et al.

With the ever-growing size of real-world graphs, numerous techniques to overcome resource limitations when training Graph Neural Networks (GNNs) have been developed. One such approach, GNNAutoScale (GAS), uses graph partitioning to enable training under constrained GPU memory. GAS also stores historical embedding vectors, which are retrieved from one-hop neighbors in other partitions, ensuring critical information is captured across partition boundaries. The historical embeddings which come from the previous training iteration are stale compared to the GAS estimated embeddings, resulting in approximation errors of the training algorithm. Furthermore, these errors accumulate over multiple layers, leading to suboptimal node embeddings. To address this shortcoming, we propose two enhancements: first, WaveGAS, inspired by waveform relaxation, performs multiple forward passes within GAS before the backward pass, refining the approximation of historical embeddings and gradients to improve accuracy; second, a gradient-tracking method that stores and utilizes more accurate historical gradients during training. Empirical results show that WaveGAS enhances GAS and achieves better accuracy, even outperforming methods that train on full graphs, thanks to its robust estimation of node embeddings.

Nhan H. Pham, Lam M. Nguyen, Jie Chen et al.

In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evaluate the robustness of c-MARL agents via a model-based approach, named c-MBA. Our proposed formulation can craft much stronger adversarial state perturbations of c-MARL agents to lower total team rewards than existing model-free approaches. In addition, we propose the first victim-agent selection strategy and the first data-driven approach to define targeted failure states where each of them allows us to develop even stronger adversarial attack without the expert knowledge to the underlying environment. Our numerical experiments on two representative MARL benchmarks illustrate the advantage of our approach over other baselines: our model-based attack consistently outperforms other baselines in all tested environments.

Hoang Thanh Lam, Gabriele Picco, Yufang Hou et al.

In many machine learning tasks, models are trained to predict structure data such as graphs. For example, in natural language processing, it is very common to parse texts into dependency trees or abstract meaning representation (AMR) graphs. On the other hand, ensemble methods combine predictions from multiple models to create a new one that is more robust and accurate than individual predictions. In the literature, there are many ensembling techniques proposed for classification or regression problems, however, ensemble graph prediction has not been studied thoroughly. In this work, we formalize this problem as mining the largest graph that is the most supported by a collection of graph predictions. As the problem is NP-Hard, we propose an efficient heuristic algorithm to approximate the optimal solution. To validate our approach, we carried out experiments in AMR parsing problems. The experimental results demonstrate that the proposed approach can combine the strength of state-of-the-art AMR parsers to create new predictions that are more accurate than any individual models in five standard benchmark datasets.

Gabriele Picco, Hoang Thanh Lam, Marco Luca Sbodio et al.

Automated Theorem Proving (ATP) deals with the development of computer programs being able to show that some conjectures (queries) are a logical consequence of a set of axioms (facts and rules). There exists several successful ATPs where conjectures and axioms are formally provided (e.g. formalised as First Order Logic formulas). Recent approaches, such as (Clark et al., 2020), have proposed transformer-based architectures for deriving conjectures given axioms expressed in natural language (English). The conjecture is verified through a binary text classifier, where the transformers model is trained to predict the truth value of a conjecture given the axioms. The RuleTaker approach of (Clark et al., 2020) achieves appealing results both in terms of accuracy and in the ability to generalize, showing that when the model is trained with deep enough queries (at least 3 inference steps), the transformers are able to correctly answer the majority of queries (97.6%) that require up to 5 inference steps. In this work we propose a new architecture, namely the Neural Unifier, and a relative training procedure, which achieves state-of-the-art results in term of generalisation, showing that mimicking a well-known inference procedure, the backward chaining, it is possible to answer deep queries even when the model is trained only on shallow ones. The approach is demonstrated in experiments using a diverse set of benchmark data.

Tran Ngoc Minh, Mathieu Sinn, Hoang Thanh Lam et al.

Data preparation, i.e. the process of transforming raw data into a format that can be used for training effective machine learning models, is a tedious and time-consuming task. For image data, preprocessing typically involves a sequence of basic transformations such as cropping, filtering, rotating or flipping images. Currently, data scientists decide manually based on their experience which transformations to apply in which particular order to a given image data set. Besides constituting a bottleneck in real-world data science projects, manual image data preprocessing may yield suboptimal results as data scientists need to rely on intuition or trial-and-error approaches when exploring the space of possible image transformations and thus might not be able to discover the most effective ones. To mitigate the inefficiency and potential ineffectiveness of manual data preprocessing, this paper proposes a deep reinforcement learning framework to automatically discover the optimal data preprocessing steps for training an image classifier. The framework takes as input sets of labeled images and predefined preprocessing transformations. It jointly learns the classifier and the optimal preprocessing transformations for individual images. Experimental results show that the proposed approach not only improves the accuracy of image classifiers, but also makes them substantially more robust to noisy inputs at test time.

Han Qiu, Hoang Thanh Lam, Francesco Fusco et al.

We propose an approximation algorithm for efficient correlation search in time series data. In our method, we use Fourier transform and neural network to embed time series into a low-dimensional Euclidean space. The given space is learned such that time series correlation can be effectively approximated from Euclidean distance between corresponding embedded vectors. Therefore, search for correlated time series can be done using an index in the embedding space for efficient nearest neighbor search. Our theoretical analysis illustrates that our method's accuracy can be guaranteed under certain regularity conditions. We further conduct experiments on real-world datasets and the results show that our method indeed outperforms the baseline solution. In particular, for approximation of correlation, our method reduces the approximation loss by a half in most test cases compared to the baseline solution. For top-$k$ highest correlation search, our method improves the precision from 5\% to 20\% while the query time is similar to the baseline approach query time.

Hoang Thanh Lam, Tran Ngoc Minh, Mathieu Sinn et al.

Feature engineering is one of the most important but most tedious tasks in data science. This work studies automation of feature learning from relational database. We first prove theoretically that finding the optimal features from relational data for predictive tasks is NP-hard. We propose an efficient rule-based approach based on heuristics and a deep neural network to automatically learn appropriate features from relational data. We benchmark our approaches in ensembles in past Kaggle competitions. Our new approach wins late medals and beats the state-of-the-art solutions with significant margins. To the best of our knowledge, this is the first time an automated data science system could win medals in Kaggle competitions with complex relational database.

Hoang Thanh Lam, Johann-Michael Thiebaut, Mathieu Sinn et al.

Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to discover relevant hand-crafted features from raw data. In this paper, we introduce a system called One Button Machine, or OneBM for short, which automates feature discovery in relational databases. OneBM automatically performs a key activity of data scientists, namely, joining of database tables and applying advanced data transformations to extract useful features from data. We validated OneBM in Kaggle competitions in which OneBM achieved performance as good as top 16% to 24% data scientists in three Kaggle competitions. More importantly, OneBM outperformed the state-of-the-art system in a Kaggle competition in terms of prediction accuracy and ranking on Kaggle leaderboard. The results show that OneBM can be useful for both data scientists and non-experts. It helps data scientists reduce data exploration time allowing them to try and error many ideas in short time. On the other hand, it enables non-experts, who are not familiar with data science, to quickly extract value from their data with a little effort, time and cost.

Hoang Thanh Lam, Ernesto Diaz-Aviles, Alessandra Pascale et al.

Real-time estimation of destination and travel time for taxis is of great importance for existing electronic dispatch systems. We present an approach based on trip matching and ensemble learning, in which we leverage the patterns observed in a dataset of roughly 1.7 million taxi journeys to predict the corresponding final destination and travel time for ongoing taxi trips, as a solution for the ECML/PKDD Discovery Challenge 2015 competition. The results of our empirical evaluation show that our approach is effective and very robust, which led our team -- BlueTaxi -- to the 3rd and 7th position of the final rankings for the trip time and destination prediction tasks, respectively. Given the fact that the final rankings were computed using a very small test set (with only 320 trips) we believe that our approach is one of the most robust solutions for the challenge based on the consistency of our good results across the test sets.

Ernesto Diaz-Aviles, Hoang Thanh Lam, Fabio Pinelli et al.

Collaborative Filtering (CF) is a core component of popular web-based services such as Amazon, YouTube, Netflix, and Twitter. Most applications use CF to recommend a small set of items to the user. For instance, YouTube presents to a user a list of top-n videos she would likely watch next based on her rating and viewing history. Current methods of CF evaluation have been focused on assessing the quality of a predicted rating or the ranking performance for top-n recommended items. However, restricting the recommender system evaluation to these two aspects is rather limiting and neglects other dimensions that could better characterize a well-perceived recommendation. In this paper, instead of optimizing rating or top-n recommendation, we focus on the task of predicting which items generate the highest user engagement. In particular, we use Twitter as our testbed and cast the problem as a Collaborative Ranking task where the rich features extracted from the metadata of the tweets help to complement the transaction information limited to user ids, item ids, ratings and timestamps. We learn a scoring function that directly optimizes the user engagement in terms of nDCG@10 on the predicted ranking. Experiments conducted on an extended version of the MovieTweetings dataset, released as part of the RecSys Challenge 2014, show the effectiveness of our approach.