United States

Cryo-electron microscopy (cryo-EM) has revolutionized the field of structural biology, determining structures of large protein machines and sharpening the understanding of fundamental biological processes. Despite cryo-EM’s unique capacity to discover novel proteins from unpurified samples and reveal the intricate structures of protein complexes within native cellular environments, the advancement of protein identification methods for cryo-EM lags behind. Without prior knowledge, such as sequence, protein identification from low-resolution density maps remains challenging. Here we introduce CryoDomain, an innovative method for identifying protein domains — conserved constituent units of proteins — from low-resolution cryo-EM density maps without requiring prior knowledge of protein sequences. CryoDomain leverages cross-modal alignment to correlate cryo-EM density maps with atomic structures, transferring the knowledge learned on a large atomic structure dataset to a sparse density map dataset. On two protein domain benchmarks constructed from CATH and SCOPe, CryoDomain significantly outperforms the state-of-the-art methods for domain identification from low-resolution density maps. CryoDomain liberates structural biologists from the tedious tasks of density inspection and database searching during protein identification. It has the potential to extend the border of unbiased structure discovery and cellular landscape investigation using cryo-EM.

AAAI 2025

CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps

natural sciences

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Large Language Models (LLMs) possess vast amounts of knowledge within their parameters, prompting research into methods for locating and editing this knowledge. Previous work has largely focused on locating entity-related (often _single-token_) facts in smaller models. However, several key questions remain unanswered: (1) _How can we effectively locate query-relevant neurons in contemporary autoregressive LLMs, such as Llama and Mistral?_ (2) _How can we address the challenge of long-form text generation?_ (3) _Are there localized knowledge regions in LLMs?_ In this study, we introduce Query-Relevant Neuron Cluster Attribution (QRNCA), a novel architecture-agnostic framework capable of identifying query-relevant neurons in LLMs. QRNCA allows for the examination of long-form answers beyond triplet facts by employing the proxy task of multi-choice question answering. To evaluate the effectiveness of our detected neurons, we build two multi-choice QA datasets spanning diverse domains and languages. Empirical evaluations demonstrate that our method outperforms baseline methods significantly. Further, analysis of neuron distributions reveals the presence of visible localized regions, particularly within different domains. Finally, we show potential applications of our detected neurons in knowledge editing and neuron-based prediction.

Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts

Multi-Agent Path Finding (MAPF) is the problem of planning collision-free paths for multiple agents. Unfortunately, during the execution of a MAPF plan, agents may suffer from unexpected delays. Given such delays, Switchable Temporal Plan Graph (STPG) provides a framework to search for an acyclic Temporal Plan Graph (TPG) with the minimum execution cost, which guarantees deadlock- and collision-free execution. However, existing optimal algorithms like Mixed-Integer Linear Programming (MILP) or Graph-Based Switchable Edge Search (GSES) are too slow. This paper speeds up GSES with four techniques: stronger admissible heuristics, edge grouping, prioritized branching, and incremental implementation. Experimenting on 4 different types of maps with varying numbers of agents, our method, Improved GSES (IGSES), consistently achieves more than double the success rates of GSES and demonstrates up to a 30-fold speedup on instances where both methods find solutions.

Speedup Techniques for Switchable Temporal Plan Graph Optimization

Somatic Contiguous Hypermutations (CHM) are a popular variation operator used in artificial immune systems for optimisation tasks. 
Theoretical studies have shown that CHM operators can lead to considerable speed-ups in the expected optimisation time compared to the traditional standard bit mutation (SBM) operators used in evolutionary computation for both single-objective and multi-objective problems where it is advantageous to mutate large contiguous areas of the genotype representing the candidate solutions. These speed-ups can make the difference between polynomial and exponential runtimes, but come at the expense of the CHM operator being considerably slower than the SBM operator in easy hillclimbing phases of the optimisation process, when small areas of the genotype have to be mutated for progress to be made. In this paper we present a Fast CHM operator that is asymptotically just as fast as traditional SBM for hillclimbing yet maintains the efficacy of the standard CHM operator when large jumps in the search space are required to make progress efficiently.
We demonstrate such efficacy on all applications were CHM has been previously studied in the literature.

Fast Contiguous Somatic Hypermutations for Single-Objective Optimisation and Multi-Objective Optimisation Via Decomposition

The clique partitioning problem (CPP) aims to find a partition of vertices of a complete graph in order to maximize the sum of edge weights within each partition (clique), which has been proven to be NP-hard and has wide real-world applications. In this paper, we propose an elite-guided weighted simulated annealing algorithm called EWSA to solve the CPP. First, EWSA employs two specific configurations and alternates between them via an oscillation strategy, which balances the exploitation and exploration of the search. Second, a weighting strategy is introduced to improve the scoring function in traditional simulated annealing, which is able to guide the search to explore diverse solutions. Finally, a partition restriction strategy is adopted to reduce search space and increase the search efficiency. Experiments on 255 instances demonstrate the competitiveness of EWSA. For 130 open instances, EWSA discovers new upper bounds in 32 cases and matches the best known results for the others. For the remaining 125 closed instances, EWSA achieves the best known objective values within a short computational time.

An Elite-guided Weighted Simulated Annealing Algorithm for the Clique Partitioning Problem

A graph $G$ is $c$-closed if any two vertices with at least $c$ common neighbors are adjacent to each other. Introduced by Fox, Roughgarden, Seshadhri, Wei and Wein [ICALP 2018, SICOMP 2020], this definition is an abstraction of the triadic closure property exhibited by many real-world social networks, namely, friends of friends tend to be friends themselves. Social networks, however, are temporal rather than static---the connections  change over a period of time. And hence temporal graphs, rather than static graphs, are often better suited to model social networks. Motivated by this, we introduce a definition of temporal $c$-closed graphs, in which if two vertices $u$ and $v$ have at least $c$ common neighbors during a short interval of time, then $u$ and $v$ are adjacent to each other around that time. Our pilot experiments show that several real-world temporal networks are indeed $c$-closed for rather small values of $c$. We also study the computational problems of enumerating maximal cliques and similar dense subgraphs in temporal $c$-closed  graphs; a clique in a temporal graph is a subgraph that lasts for a certain period of time, during which every possible edge in the subgraph becomes active often enough, and other dense subgraphs are defined similarly. We bound the number of such maximal dense subgraphs, and thus show that the corresponding enumeration problems admit efficient algorithms, provided the graph evolves slowly over time; by slow evolution, we mean that between consecutive time-steps, the local change in adjacencies remains small. Our work also adds to a growing body of literature on defining suitable structural parameters for temporal graphs that can be leveraged to design efficient algorithms.

Temporal Triadic Closure: Finding Dense Substructures in Social Networks That Evolve over Time

Explainable AI increasingly relies on argumentation methods to facilitate interactive explanations between AI agents and human users. While most works assume a known human user model as a prior, there is a critical gap in effectively learning and updating these models dynamically. In this paper, we address this gap with a framework that enables AI agents to learn and update probabilistic human models through argumentation-based dialogues. Specifically, our approach, called Persona, is inspired by prospect theory and integrates a probability weighting function with a Bayesian belief update mechanism that refines a probability distribution over possible human models based on exchanged arguments. Through empirical evaluations with human users in an applied argumentation setting, we demonstrate the effectiveness of Persona in capturing evolving human beliefs and facilitating personalized interactions, while also outperforming state-of-the-art methods.

Does Your AI Agent Get You? A Personalizable Framework for Approximating Human Models from Argumentation-based Dialogue Traces

Sequential Recommender Systems (SRS), which model a user's interaction history to predict the next item of interest, are widely used in various applications. However, existing SRS often struggle with low-popularity items, a challenge known as the long-tail problem. This issue leads to reduced serendipity for users and diminished profits for sellers, ultimately harming the overall system. Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity, making them a promising solution to this problem. In this paper, we introduce __LLMEmb__, a novel method leveraging LLM to generate item embeddings that enhance SRS performance. To bridge the gap between general-purpose LLM and the recommendation domain, we propose a Supervised Contrastive Fine-Tuning (SCFT) approach. This approach includes attribute-level data augmentation and a tailored contrastive loss to make LLM more recommendation-friendly. Additionally, we emphasize the importance of integrating collaborative signals into LLM-generated embeddings, for which we propose Recommendation Adaptation Training (RAT). This further refines the embeddings for optimal use in SRS. The LLMEmb-derived embeddings can be seamlessly integrated with any SRS model, underscoring the practical value. Comprehensive experiments conducted on three real-world datasets demonstrate that LLMEmb significantly outperforms existing methods across multiple SRS models. The code for our method is provided in the __Supplementary Materials__.

LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation

Text-to-SQL enables users to interact with databases through natural language, simplifying the retrieval and synthesis of information. Despite the success of large language models (LLMs) in converting natural language questions into SQL queries, their broader adoption is limited by two main challenges: achieving robust generalization across diverse queries and ensuring interpretative confidence in their predictions. To tackle these issues, our research investigates the integration of selective classifiers into text-to-SQL systems. 
We analyse the trade-off between coverage and risk using entropy based confidence estimation with selective classifiers and assess its impact on the overall performance of text-to-SQL models.  Additionally, we explore the models' initial calibration and improve it with calibration techniques for better model alignment between confidence and accuracy.  Our experimental results show that encoder-decoder T5 is better calibrated than in-context-learning GPT 4 and decoder-only Llama 3, thus the designated external entropy-based selective classifier has better performance.  The study also reveal that, in terms of error detection, selective classifier with a higher probability detects errors associated with irrelevant questions rather than incorrect query generations.

Confidence Estimation for Error Detection in Text-to-SQL Systems

Opponent Modeling (OM) aims to enhance decision-making by modeling other agents in multi-agent environments. Existing works typically learn opponent models against a pre-designated fixed set of opponents during training. However, this will cause poor generalization when facing unknown opponents during testing, as previously unseen opponents can exhibit out-of-distribution (OOD) behaviors that the learned opponent models cannot handle. To tackle this problem, we introduce a novel Open-Ended Opponent Modeling (OEOM) framework, which continuously generates opponents with diverse strengths and styles to reduce the possibility of OOD situations occurring during testing. Founded on population-based training and information-theoretic trajectory space diversity regularization, OEOM generates a dynamic set of opponents. This set is then fed to any OM approaches to train a potentially generalizable opponent model. Upon this, we further propose a simple yet effective OM approach that naturally fits within the OEOM framework. This approach is based on in-context reinforcement learning and learns a Transformer that dynamically recognizes and responds to opponents based on their trajectories. Extensive experiments in cooperative, competitive, and mixed environments demonstrate that OEOM is an approach-agnostic framework that improves generalizability compared to training against a fixed set of opponents, regardless of OM approaches or testing opponent settings. The results also indicate that our proposed approach generally outperforms existing OM baselines.

An Open-Ended Learning Framework for Opponent Modeling

Drafting radiology reports is a complex task requiring flexibility, where radiologists need to adjust the content based on the information available and particular clinical demands. However, most current automated radiology report generation (RRG) models are constrained to a fixed task paradigm, such as predicting the complete ``finding'' section from a single image. Such a fixed task paradigm inherently involves a mismatch between inputs and outputs. The trained models lack the flexibility for diverse inputs and could generate harmful, input-agnostic hallucinations. To bridge the gap between current RRG models and the clinical demands in practice, we first develop a data generation pipeline to create a new MIMIC-RG4 dataset, which considers four common radiology report drafting scenarios and has perfectly corresponded input and output. Secondly, we propose a novel large language model (LLM) based RRG framework, namely LLM-RG4, which utilizes LLM as the text decoder to leverage its flexible instruction-following capabilities and extensive general knowledge. We further develop an adaptive token fusion module that offers flexibility to handle diverse scenarios with different input combinations, while minimizing the additional computational burden associated with increased input volumes. Besides, we propose a token-level loss weighting strategy to direct the model's attention towards positive and uncertain descriptions, which are essential for accurate clinical diagnosis. Experimental results demonstrate that LLM-RG4 achieves state-of-the-art performance in both clinical efficiency and natural language generation on the MIMIC-RG4 and MIMIC-CXR datasets. We quantitatively demonstrate that our model has minimal input-agnostic hallucinations, whereas current open-source models commonly suffer from this problem.

CryoDomain: Sequence-free Protein Domain Identification from Low-resolution Cryo-EM Density Maps

Downloads

Next from AAAI 2025

Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES