[HN Gopher] Knowledge Graph Reasoning Based on Attention GCN
       ___________________________________________________________________
        
       Knowledge Graph Reasoning Based on Attention GCN
        
       Author : PaulHoule
       Score  : 40 points
       Date   : 2023-12-28 16:02 UTC (6 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | vinni2 wrote:
       | I don't get why this paper is newsworthy!
        
         | Jeff_Brown wrote:
         | I can speak to neural networks and graphs generally, if not
         | this specific paper. Neural networks can do reasoning, but
         | their internal representation of information is illegible.
         | Graphs let us represent information legibly.
        
           | hyperliner wrote:
           | As an ignorant person but one who has been trying to figure
           | out if KGs are superseded by LLMs, is there a source you can
           | think of to figure out if both have a place in an
           | architecture, or if LLMs are sufficient? What sort of use
           | cases require both?
        
             | hansvm wrote:
             | Current performant (high accuracy) LLMs have a quadratic
             | cost (space and time) in sequence length, they have a
             | finite size typically much less than any KG of note, their
             | connections are all fuzzy, they aren't especially amenable
             | to small updates, training and fine-tuning don't work well
             | with high-entropy data, and most computations physically
             | cannot be done via any single pass through an LLM
             | regardless of how it was trained.
             | 
             | Those constraints together create a landscape where if you
             | have a big knowledge graph there will invariably be
             | important questions the LLM cannot appropriately answer
             | about it, no matter which strategy you use to try to ramrod
             | the KG into an LLM architecture. If you don't train/fine-
             | tune the LLM on the KG, it doesn't have enough context to
             | answer your questions. If you do, your KG doesn't have
             | enough data duplication to allow training to work well. If
             | you manage to train it anyway, you can't ask compounded
             | questions because of the max LLM circuit depth. If you try
             | anyway and just run the results back into the LLM as input
             | you have a compounding error effect because the whole thing
             | is fuzzy. If you try to circumvent that with error-
             | reduction techniques you tend to blow through the current
             | context windows (quadratic costs) and still have unreliable
             | results. And so on.
             | 
             | None of that is necessarily true forever, but suppose you
             | have a problem where a KG is a natural fit but some of the
             | data is a little fuzzy (you have pretty good graphs of how
             | cities and roads and individuals and companies and whatnot
             | are related, but it's not perfect, and some of it is
             | textual or not otherwise appropriately structured). The KG
             | can answer a number of queries very well, limited by the
             | lack of structure in the node/edge representations. An LLM
             | can't do much because it can't compress all those possible
             | edges into its weights, because it can't fit the whole KG
             | in a context window, it can't be appropriately fine-tuned
             | to the data, and even if it could it couldn't recurse well
             | without compounding error. If you instead use the LLM as a
             | pre-processing step on the nodes or as a fuzzy neighbor
             | search (restricted by the KG) or in some other way, you get
             | a data structure that looks a lot more like a better
             | prepared clean KG and can run traditional KG algorithms to
             | ask questions like who might need your tax prep services or
             | whatever. Getting an LLM to do that for the same cost will
             | take a _ton_ of engineering beyond what I've seen poured
             | into the space.
        
           | Byamarro wrote:
           | I'm a complete layman, but it sounds awfully like that one
           | problem I've once encountered on the Wikipedia: https://en.m.
           | wikipedia.org/wiki/Explainable_artificial_intel...
        
       | westurner wrote:
       | "Snomed CT Entity Linking Challenge"
       | https://news.ycombinator.com/item?id=38744177 :
       | 
       | > _- Indicate degree of confidence in annotation (note that AGI
       | hypergraph systems have TruthValue and also AttentionValue, like
       | attention networks_
       | 
       | From "AutoML-Zero: Evolving Code That Learns"
       | https://news.ycombinator.com/item?id=23787359 :
       | 
       | > _How does this compare to MOSES (OpenCog /asmoses) or PLN?
       | https://github.com/opencog/asmoses
       | https://scholar.google.com/scholar?hl=en&as_sdt=0%2C43&q=%22..._
       | (2006)
       | 
       | opencog/atomspace is a hypergraph for knowledge graphs with
       | TruthValue and AttentionValue.
       | https://github.com/opencog/atomspace
       | 
       | examples/python/create_atoms_simple.py:
       | https://github.com/opencog/atomspace/blob/master/examples/py...
       | 
       | - [ ] Clone Atomspace hypergraph with RDFstar and SPARQLstar.
       | 
       | ONNX is a standard and also now an ecosystem for exchange of
       | neural networks.
       | https://en.wikipedia.org/wiki/Open_Neural_Network_Exchange
       | 
       | RDFHDT: RDF Header, Dictionary, Triples: is fast to read but not
       | write.
       | 
       | From https://news.ycombinator.com/item?id=35810320 :
       | 
       | > _Is there a better way to publish Linked Data with existing
       | tools like LaTeX, PDF, or Word? Which support CSVW? Which support
       | RDF /RDFa/JSON-LD?_
        
       | pama wrote:
       | How does the recently proved zero-one theorem for graph neural
       | networks affect such works? https://arxiv.org/abs/2301.13060
        
       ___________________________________________________________________
       (page generated 2023-12-28 23:01 UTC)